{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Project 1: Standardized Testing, Statistical Summaries and Inference\n", "\n", "### Marco Tavora" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Overview \n", "\n", "Suppose that the College Board, a nonprofit organization responsible for administering the SAT (Scholastic Aptitude Test), seeks to increase the rate of high-school graduates who participate in its exams. This project's aim is to make recommendations about which measures the College Board might take in order to achieve that." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Problem Statement\n", "\n", "The problem we need to solve is to how to make actionable suggestions to the College Board to help them increase the participation rates in their exams. For that we need to perform an exploratory data analysis (EDA) to find appropriate metrics that can be adjusted by the College Board accordingly. \n", "\n", "Performing the EDA we must among other things:\n", "\n", "- Find relevants patterns in the data \n", "- Search for possible relations between subsets of the data (for example, are scores and participation rates correlated? If yes how?)\n", "- Test hypotheses about the data using statistical inference method\n", "- Identify possible biases in the data and, if possible, suggest corrections\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Brief introduction to the data\n", "\n", "The data is based on the SAT and the ACT (which stands for American College Testing and it is administered by another institution, namely, the ACT. Inc) exams from around the United States in 2017.\n", "\n", "The data contains:\n", "\n", "- Average SAT and ACT scores by state (scores for each section of each exam);\n", "\n", "- Participation rates for both exams by state.\n", "\n", "Both SAT and ACT are standardized tests for college admissions and are similar in content type but have some differences in structure. A few relevant differences are:\n", "\n", "- The ACT has a Science Test and the SAT does not;\n", "\n", "- There is a SAT Math Section for which the student is not allowed to use a calculator; \n", "\n", "- The SAT's College Board joins Reading and Writing into one score, the \"Evidence-Based Reading and Writing\" whereas in the ACT the tests are separated. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## EDA Steps" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Step 0: Importing basic modules" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We first need to import Python libraries including:\n", "- `Pandas`, for data manipulation and analysis \n", "- `SciPy` which is a Python-based ecosystem of software for mathematics, science, and engineering. \n", "- `NumPy` which is a library consisting of multidimensional array objects and a collection of routines for processing of array. \n", "- `Statsmodels` which is a Python package that allows users to explore data, estimate statistical models, and perform statistical tests and complements `SciPy`;\n", "- `Matplotlib` is a plotting library for the Python and NumPy;\n", "- `Seaborn` is complimentary to Matplotlib and it specifically targets statistical data visualization\n", "- `Pylab` is embedded inside Matplotlib and provides a Matlab-like experience for the user. It imports portions of Matplotlib and NumPy.\n", "\n", "OBS: This information was taken directly from the documentation." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/marcotavora/Applications/anaconda3/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n", " from pandas.core import datetools\n" ] } ], "source": [ "import scipy\n", "import pandas as pd\n", "import scipy.stats as stats\n", "import numpy as np\n", "import csv\n", "import statsmodels.api as sm\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "sns.set_style(\"darkgrid\")\n", "import pytest\n", "import pylab as p\n", "%matplotlib inline\n", "import pandas as pd\n", "from IPython.core.interactiveshell import InteractiveShell\n", "InteractiveShell.ast_node_interactivity = \"all\" # so we can see the value of multiple statements at once.\n", "pd.set_option('display.max_columns', None)\n", "pd.set_option('display.max_rows', None)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Step 1: Load the data and perform basic operations." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 1 & 2. Load the data in, using pandas, and print the first ten rows of each DataFrame.\n", "\n", "We can refer to the Pandas module using the \"dot notation\" to call its *methods*. To read our data (which is in the form of `csv` files), into a so-called DataFrame structure, we use the method `read_csv()` and pass in each file name as a string:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Unnamed: 0StateParticipationEvidence-Based Reading and WritingMathTotal
00Alabama5%5935721165
11Alaska38%5475331080
22Arizona30%5635531116
33Arkansas3%6145941208
44California53%5315241055
55Colorado11%6065951201
66Connecticut100%5305121041
77Delaware100%503492996
88District of Columbia100%482468950
99Florida83%5204971017
\n", "
" ], "text/plain": [ " Unnamed: 0 State Participation \\\n", "0 0 Alabama 5% \n", "1 1 Alaska 38% \n", "2 2 Arizona 30% \n", "3 3 Arkansas 3% \n", "4 4 California 53% \n", "5 5 Colorado 11% \n", "6 6 Connecticut 100% \n", "7 7 Delaware 100% \n", "8 8 District of Columbia 100% \n", "9 9 Florida 83% \n", "\n", " Evidence-Based Reading and Writing Math Total \n", "0 593 572 1165 \n", "1 547 533 1080 \n", "2 563 553 1116 \n", "3 614 594 1208 \n", "4 531 524 1055 \n", "5 606 595 1201 \n", "6 530 512 1041 \n", "7 503 492 996 \n", "8 482 468 950 \n", "9 520 497 1017 " ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sat = pd.read_csv('sat.csv')\n", "sat.head(10)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Unnamed: 0StateParticipationEnglishMathReadingScienceComposite
00National60%20.320.721.421.021.0
11Alabama100%18.918.419.719.419.2
22Alaska65%18.719.820.419.919.8
33Arizona62%18.619.820.119.819.7
44Arkansas100%18.919.019.719.519.4
55California31%22.522.723.122.222.8
66Colorado100%20.120.321.220.920.8
77Connecticut31%25.524.625.624.625.2
88Delaware18%24.123.424.823.624.1
99District of Columbia32%24.423.524.923.524.2
\n", "
" ], "text/plain": [ " Unnamed: 0 State Participation English Math Reading \\\n", "0 0 National 60% 20.3 20.7 21.4 \n", "1 1 Alabama 100% 18.9 18.4 19.7 \n", "2 2 Alaska 65% 18.7 19.8 20.4 \n", "3 3 Arizona 62% 18.6 19.8 20.1 \n", "4 4 Arkansas 100% 18.9 19.0 19.7 \n", "5 5 California 31% 22.5 22.7 23.1 \n", "6 6 Colorado 100% 20.1 20.3 21.2 \n", "7 7 Connecticut 31% 25.5 24.6 25.6 \n", "8 8 Delaware 18% 24.1 23.4 24.8 \n", "9 9 District of Columbia 32% 24.4 23.5 24.9 \n", "\n", " Science Composite \n", "0 21.0 21.0 \n", "1 19.4 19.2 \n", "2 19.9 19.8 \n", "3 19.8 19.7 \n", "4 19.5 19.4 \n", "5 22.2 22.8 \n", "6 20.9 20.8 \n", "7 24.6 25.2 \n", "8 23.6 24.1 \n", "9 23.5 24.2 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "act = pd.read_csv('act.csv')\n", "act.head(10)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Note that the first columns of both tables seem to be identical to the DataFrame indexes. We can quickly confirm that using an `assert` statement. When an `assert` statement is encountered, Python evaluates it and if the expression is false raises an `AssertionError` exception (from www.tutorialspoint.com)." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "assert (sat.index.tolist() == sat['Unnamed: 0'].tolist())\n", "assert (act.index.tolist() == act['Unnamed: 0'].tolist())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "From the the box above we are allowed to drop the first columns of both DataFrames.\n", "\n", "Next, I renamed the column \"Evidence-Based Reading and Writing\" as \"EBRW\" to be able to use methods on it via the dot notation. \n", "\n", "Dropping also the last column of the SAT table (which is just the sum of the two previous ones) and the last row and renaming the others we obtain the following DataFrame for the SAT scores:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipationEBRWMath
0Alabama5%593572
1Alaska38%547533
2Arizona30%563553
3Arkansas3%614594
4California53%531524
\n", "
" ], "text/plain": [ " State Participation EBRW Math\n", "0 Alabama 5% 593 572\n", "1 Alaska 38% 547 533\n", "2 Arizona 30% 563 553\n", "3 Arkansas 3% 614 594\n", "4 California 53% 531 524" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cols_to_keep = ['State', 'Participation', 'Evidence-Based Reading and Writing', 'Math']\n", "sat = sat[cols_to_keep]\n", "sat.columns = ['State', 'Participation', 'EBRW', 'Math']\n", "sat.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As with the SAT DataFrame, we drop last column of the ACT DataFrame (the Composite score is, according to the ACT website, just the average of the four other test scores, rounded to the nearest whole number).\n", "\n", "Furthermore, I used the `.iloc( )` method to exclude the first row of the ACT frame since it is just a summary row." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipationEBRWMath
0Alabama5%593572
1Alaska38%547533
2Arizona30%563553
3Arkansas3%614594
4California53%531524
\n", "
" ], "text/plain": [ " State Participation EBRW Math\n", "0 Alabama 5% 593 572\n", "1 Alaska 38% 547 533\n", "2 Arizona 30% 563 553\n", "3 Arkansas 3% 614 594\n", "4 California 53% 531 524" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipationEnglishMathReadingScience
1Alabama100%18.918.419.719.4
2Alaska65%18.719.820.419.9
3Arizona62%18.619.820.119.8
4Arkansas100%18.919.019.719.5
5California31%22.522.723.122.2
\n", "
" ], "text/plain": [ " State Participation English Math Reading Science\n", "1 Alabama 100% 18.9 18.4 19.7 19.4\n", "2 Alaska 65% 18.7 19.8 20.4 19.9\n", "3 Arizona 62% 18.6 19.8 20.1 19.8\n", "4 Arkansas 100% 18.9 19.0 19.7 19.5\n", "5 California 31% 22.5 22.7 23.1 22.2" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cols_to_keep = ['State', 'Participation', 'English', 'Math', 'Reading', 'Science']\n", "act = act.iloc[1:][cols_to_keep]\n", "sat.head()\n", "act.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 3. Describe in words what each variable (column) is.\n", "\n", "\n", "**SAT**\n", " \n", "The table displays three different averages for each state: \n", " - The first column is the state \n", " - The second column is the average participation of students in each state\n", " - The third and fourth columns are the average scores in the Math and Evidence-Based Reading and Writing tests (the name EBRW is explained above).\n", "\n", "**ACT**\n", " \n", "The table displays the following averages for each State: \n", " - The first column is the state \n", " - The second column is the average participation of students in that state\n", " - The third, fourth, fifth and sixth columns are the scores in the English, Math, Reading and Science tests" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 4. Does the data look complete? Are there any obvious issues with the observations?\n", "\n", "We can look for problems with the data for example:\n", "\n", "- Using `info()` \n", "- Using `describe()`\n", "- Looking at the last rows and or last columns which frequently contain aggregate values\n", "- Looking for null values\n", "- Outliers\n", "\n", "The third item was taken care of. There were no null values but there are outliers as we shall see when we perform the plotting." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "State False\n", "Participation False\n", "EBRW False\n", "Math False\n", "dtype: bool\n", "State False\n", "Participation False\n", "English False\n", "Math False\n", "Reading False\n", "Science False\n", "dtype: bool\n" ] } ], "source": [ "df_sat = sat.copy() # making copies to keep original ones intact\n", "df_act = act.copy() # making copies to keep original ones intact\n", "print (df_sat.isnull().any())\n", "print (df_act.isnull().any())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 5. Print the types of each column." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "State object\n", "Participation object\n", "EBRW int64\n", "Math int64\n", "dtype: object\n", "State object\n", "Participation object\n", "English float64\n", "Math float64\n", "Reading float64\n", "Science float64\n", "dtype: object\n" ] } ], "source": [ "print (sat.dtypes)\n", "print (act.dtypes)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 6. Do any types need to be reassigned? If so, go ahead and do it.\n", "\n", "\n", "I will convert the columns 'Participation' into `floats` using a function to extract the $\\%$ but keeping the scale between 0 and 100. The `.replace( )` method takes the argument `regex` =`True` because `type('%')` = `str`. The function was based on http://pythonjourney.com/python-pandas-dataframe-convert-percent-to-float/" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "def perc_into_float(df,col):\n", " return df[col].replace('%','',regex=True).astype('float')" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "df_sat['Participation'] = perc_into_float(df_sat,'Participation')\n", "df_act['Participation'] = perc_into_float(df_act,'Participation')" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipationEBRWMath
0Alabama5.0593572
1Alaska38.0547533
\n", "
" ], "text/plain": [ " State Participation EBRW Math\n", "0 Alabama 5.0 593 572\n", "1 Alaska 38.0 547 533" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_sat.head(2)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipationEnglishMathReadingScience
1Alabama100.018.918.419.719.4
2Alaska65.018.719.820.419.9
\n", "
" ], "text/plain": [ " State Participation English Math Reading Science\n", "1 Alabama 100.0 18.9 18.4 19.7 19.4\n", "2 Alaska 65.0 18.7 19.8 20.4 19.9" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_act.head(2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Checking types again:" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "State object\n", "Participation float64\n", "EBRW int64\n", "Math int64\n", "dtype: object\n", "State object\n", "Participation float64\n", "English float64\n", "Math float64\n", "Reading float64\n", "Science float64\n", "dtype: object\n" ] } ], "source": [ "print (df_sat.dtypes)\n", "print (df_act.dtypes)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 7. Create a dictionary for each column mapping the State to its respective value for that column. (For example, you should have three SAT dictionaries.)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Answer version 1**\n", "\n", "Using a list comprehension, the command:\n", "\n", " df.set_index('State').to_dict()\n", " \n", "creates a dictionary with column names as keys. For example:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'Participation': {'Alabama': 5.0, 'Alaska': 38.0, 'Arizona': 30.0, 'Arkansas': 3.0, 'California': 53.0, 'Colorado': 11.0, 'Connecticut': 100.0, 'Delaware': 100.0, 'District of Columbia': 100.0, 'Florida': 83.0, 'Georgia': 61.0, 'Hawaii': 55.0, 'Idaho': 93.0, 'Illinois': 9.0, 'Indiana': 63.0, 'Iowa': 2.0, 'Kansas': 4.0, 'Kentucky': 4.0, 'Louisiana': 4.0, 'Maine': 95.0, 'Maryland': 69.0, 'Massachusetts': 76.0, 'Michigan': 100.0, 'Minnesota': 3.0, 'Mississippi': 2.0, 'Missouri': 3.0, 'Montana': 10.0, 'Nebraska': 3.0, 'Nevada': 26.0, 'New Hampshire': 96.0, 'New Jersey': 70.0, 'New Mexico': 11.0, 'New York': 67.0, 'North Carolina': 49.0, 'North Dakota': 2.0, 'Ohio': 12.0, 'Oklahoma': 7.0, 'Oregon': 43.0, 'Pennsylvania': 65.0, 'Rhode Island': 71.0, 'South Carolina': 50.0, 'South Dakota': 3.0, 'Tennessee': 5.0, 'Texas': 62.0, 'Utah': 3.0, 'Vermont': 60.0, 'Virginia': 65.0, 'Washington': 64.0, 'West Virginia': 14.0, 'Wisconsin': 3.0, 'Wyoming': 3.0}, 'EBRW': {'Alabama': 593, 'Alaska': 547, 'Arizona': 563, 'Arkansas': 614, 'California': 531, 'Colorado': 606, 'Connecticut': 530, 'Delaware': 503, 'District of Columbia': 482, 'Florida': 520, 'Georgia': 535, 'Hawaii': 544, 'Idaho': 513, 'Illinois': 559, 'Indiana': 542, 'Iowa': 641, 'Kansas': 632, 'Kentucky': 631, 'Louisiana': 611, 'Maine': 513, 'Maryland': 536, 'Massachusetts': 555, 'Michigan': 509, 'Minnesota': 644, 'Mississippi': 634, 'Missouri': 640, 'Montana': 605, 'Nebraska': 629, 'Nevada': 563, 'New Hampshire': 532, 'New Jersey': 530, 'New Mexico': 577, 'New York': 528, 'North Carolina': 546, 'North Dakota': 635, 'Ohio': 578, 'Oklahoma': 530, 'Oregon': 560, 'Pennsylvania': 540, 'Rhode Island': 539, 'South Carolina': 543, 'South Dakota': 612, 'Tennessee': 623, 'Texas': 513, 'Utah': 624, 'Vermont': 562, 'Virginia': 561, 'Washington': 541, 'West Virginia': 558, 'Wisconsin': 642, 'Wyoming': 626}, 'Math': {'Alabama': 572, 'Alaska': 533, 'Arizona': 553, 'Arkansas': 594, 'California': 524, 'Colorado': 595, 'Connecticut': 512, 'Delaware': 492, 'District of Columbia': 468, 'Florida': 497, 'Georgia': 515, 'Hawaii': 541, 'Idaho': 493, 'Illinois': 556, 'Indiana': 532, 'Iowa': 635, 'Kansas': 628, 'Kentucky': 616, 'Louisiana': 586, 'Maine': 499, 'Maryland': 52, 'Massachusetts': 551, 'Michigan': 495, 'Minnesota': 651, 'Mississippi': 607, 'Missouri': 631, 'Montana': 591, 'Nebraska': 625, 'Nevada': 553, 'New Hampshire': 520, 'New Jersey': 526, 'New Mexico': 561, 'New York': 523, 'North Carolina': 535, 'North Dakota': 621, 'Ohio': 570, 'Oklahoma': 517, 'Oregon': 548, 'Pennsylvania': 531, 'Rhode Island': 524, 'South Carolina': 521, 'South Dakota': 603, 'Tennessee': 604, 'Texas': 507, 'Utah': 614, 'Vermont': 551, 'Virginia': 541, 'Washington': 534, 'West Virginia': 528, 'Wisconsin': 649, 'Wyoming': 604}}\n" ] } ], "source": [ "print (df_sat.set_index('State').to_dict())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We obtain the dictionary values using\n", "\n", " [cols[i]],\n", " \n", "where `cols` are the column names and `cols[i]` are the keys for $i$ within the range of the number of columns. We then return the elements of this list of dictionaries." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "def dict_all(df,cols,n):\n", " return [df.set_index('State').to_dict()[cols[i]] for i in range(1,len(cols))][n]" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "dsat_part = dict_all(df_sat,df_sat.columns.tolist(),0)\n", "dsat_EBRW = dict_all(df_sat,df_sat.columns.tolist(),1)\n", "dsat_math = dict_all(df_sat,df_sat.columns.tolist(),2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Example:" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'Alabama': 593, 'Alaska': 547, 'Arizona': 563, 'Arkansas': 614, 'California': 531, 'Colorado': 606, 'Connecticut': 530, 'Delaware': 503, 'District of Columbia': 482, 'Florida': 520, 'Georgia': 535, 'Hawaii': 544, 'Idaho': 513, 'Illinois': 559, 'Indiana': 542, 'Iowa': 641, 'Kansas': 632, 'Kentucky': 631, 'Louisiana': 611, 'Maine': 513, 'Maryland': 536, 'Massachusetts': 555, 'Michigan': 509, 'Minnesota': 644, 'Mississippi': 634, 'Missouri': 640, 'Montana': 605, 'Nebraska': 629, 'Nevada': 563, 'New Hampshire': 532, 'New Jersey': 530, 'New Mexico': 577, 'New York': 528, 'North Carolina': 546, 'North Dakota': 635, 'Ohio': 578, 'Oklahoma': 530, 'Oregon': 560, 'Pennsylvania': 540, 'Rhode Island': 539, 'South Carolina': 543, 'South Dakota': 612, 'Tennessee': 623, 'Texas': 513, 'Utah': 624, 'Vermont': 562, 'Virginia': 561, 'Washington': 541, 'West Virginia': 558, 'Wisconsin': 642, 'Wyoming': 626}\n" ] } ], "source": [ "print( dsat_EBRW)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "dact_part = dict_all(df_sat,df_sat.columns.tolist(),0)\n", "dact_eng = dict_all(df_act,df_act.columns.tolist(),1)\n", "dact_math = dict_all(df_act,df_act.columns.tolist(),2)\n", "dact_read = dict_all(df_act,df_act.columns.tolist(),3)\n", "dact_sci = dict_all(df_act,df_act.columns.tolist(),4)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Example:" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'Alabama': 5.0, 'Alaska': 38.0, 'Arizona': 30.0, 'Arkansas': 3.0, 'California': 53.0, 'Colorado': 11.0, 'Connecticut': 100.0, 'Delaware': 100.0, 'District of Columbia': 100.0, 'Florida': 83.0, 'Georgia': 61.0, 'Hawaii': 55.0, 'Idaho': 93.0, 'Illinois': 9.0, 'Indiana': 63.0, 'Iowa': 2.0, 'Kansas': 4.0, 'Kentucky': 4.0, 'Louisiana': 4.0, 'Maine': 95.0, 'Maryland': 69.0, 'Massachusetts': 76.0, 'Michigan': 100.0, 'Minnesota': 3.0, 'Mississippi': 2.0, 'Missouri': 3.0, 'Montana': 10.0, 'Nebraska': 3.0, 'Nevada': 26.0, 'New Hampshire': 96.0, 'New Jersey': 70.0, 'New Mexico': 11.0, 'New York': 67.0, 'North Carolina': 49.0, 'North Dakota': 2.0, 'Ohio': 12.0, 'Oklahoma': 7.0, 'Oregon': 43.0, 'Pennsylvania': 65.0, 'Rhode Island': 71.0, 'South Carolina': 50.0, 'South Dakota': 3.0, 'Tennessee': 5.0, 'Texas': 62.0, 'Utah': 3.0, 'Vermont': 60.0, 'Virginia': 65.0, 'Washington': 64.0, 'West Virginia': 14.0, 'Wisconsin': 3.0, 'Wyoming': 3.0}\n" ] } ], "source": [ "print( dact_part)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Answer version 2**" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "def func_dict_v2(df,col_name):\n", " return {df['State'][i]:df[col_name][i] for i in range(df.shape[0])}" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "dsat_part_v2 = func_dict_v2(df_sat,'Participation')\n", "dsat_EBRW_v2 = func_dict_v2(df_sat,'EBRW')\n", "dsat_math_v2 = func_dict_v2(df_sat,'Math')" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "assert(dsat_math == dsat_math_v2)\n", "assert(dsat_part == dsat_part_v2)\n", "assert(dsat_math == dsat_math_v2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "But **let us use Version 1.**" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 8. Create one dictionary where each key is the column name, and each value is an iterable (a list or a Pandas Series) of all the values in that column.\n", "\n", "Using a simple dictionary comprehension." ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "def dict_col(df):\n", " return {col:df[col].tolist() for col in df.columns}" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'State': ['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut', 'Delaware', 'District of Columbia', 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland', 'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi', 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', 'New Mexico', 'New York', 'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', 'Rhode Island', 'South Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia', 'Washington', 'West Virginia', 'Wisconsin', 'Wyoming'], 'Participation': [5.0, 38.0, 30.0, 3.0, 53.0, 11.0, 100.0, 100.0, 100.0, 83.0, 61.0, 55.0, 93.0, 9.0, 63.0, 2.0, 4.0, 4.0, 4.0, 95.0, 69.0, 76.0, 100.0, 3.0, 2.0, 3.0, 10.0, 3.0, 26.0, 96.0, 70.0, 11.0, 67.0, 49.0, 2.0, 12.0, 7.0, 43.0, 65.0, 71.0, 50.0, 3.0, 5.0, 62.0, 3.0, 60.0, 65.0, 64.0, 14.0, 3.0, 3.0], 'EBRW': [593, 547, 563, 614, 531, 606, 530, 503, 482, 520, 535, 544, 513, 559, 542, 641, 632, 631, 611, 513, 536, 555, 509, 644, 634, 640, 605, 629, 563, 532, 530, 577, 528, 546, 635, 578, 530, 560, 540, 539, 543, 612, 623, 513, 624, 562, 561, 541, 558, 642, 626], 'Math': [572, 533, 553, 594, 524, 595, 512, 492, 468, 497, 515, 541, 493, 556, 532, 635, 628, 616, 586, 499, 52, 551, 495, 651, 607, 631, 591, 625, 553, 520, 526, 561, 523, 535, 621, 570, 517, 548, 531, 524, 521, 603, 604, 507, 614, 551, 541, 534, 528, 649, 604]}\n", "\n", "{'State': ['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut', 'Delaware', 'District of Columbia', 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland', 'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi', 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', 'New Mexico', 'New York', 'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', 'Rhode Island', 'South Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia', 'Washington', 'West Virginia', 'Wisconsin', 'Wyoming'], 'Participation': [100.0, 65.0, 62.0, 100.0, 31.0, 100.0, 31.0, 18.0, 32.0, 73.0, 55.0, 90.0, 38.0, 93.0, 35.0, 67.0, 73.0, 100.0, 100.0, 8.0, 28.0, 29.0, 29.0, 100.0, 100.0, 100.0, 100.0, 84.0, 100.0, 18.0, 34.0, 66.0, 31.0, 100.0, 98.0, 75.0, 100.0, 40.0, 23.0, 21.0, 100.0, 80.0, 100.0, 45.0, 100.0, 29.0, 29.0, 29.0, 69.0, 100.0, 100.0], 'English': [18.9, 18.7, 18.6, 18.9, 22.5, 20.1, 25.5, 24.1, 24.4, 19.0, 21.0, 17.8, 21.9, 21.0, 22.0, 21.2, 21.1, 19.6, 19.4, 24.2, 23.3, 25.4, 24.1, 20.4, 18.2, 19.8, 19.0, 20.9, 16.3, 25.4, 23.8, 18.6, 23.8, 17.8, 19.0, 21.2, 18.5, 21.2, 23.4, 24.0, 17.5, 20.7, 19.5, 19.5, 19.5, 23.3, 23.5, 20.9, 20.0, 19.7, 19.4], 'Math': [18.4, 19.8, 19.8, 19.0, 22.7, 20.3, 24.6, 23.4, 23.5, 19.4, 20.9, 19.2, 21.8, 21.2, 22.4, 21.3, 21.3, 19.4, 18.8, 24.0, 23.1, 25.3, 23.7, 21.5, 18.1, 19.9, 20.2, 20.9, 18.0, 25.1, 23.8, 19.4, 24.0, 19.3, 20.4, 21.6, 18.8, 21.5, 23.4, 23.3, 18.6, 21.5, 19.2, 20.7, 19.9, 23.1, 23.3, 21.9, 19.4, 20.4, 19.8], 'Reading': [19.7, 20.4, 20.1, 19.7, 23.1, 21.2, 25.6, 24.8, 24.9, 21.0, 22.0, 19.2, 23.0, 21.6, 23.2, 22.6, 22.3, 20.5, 19.8, 24.8, 24.2, 25.9, 24.5, 21.8, 18.8, 20.8, 21.0, 21.9, 18.1, 26.0, 24.1, 20.4, 24.6, 19.6, 20.5, 22.5, 20.1, 22.4, 24.2, 24.7, 19.1, 22.3, 20.1, 21.1, 20.8, 24.4, 24.6, 22.1, 21.2, 20.6, 20.8], 'Science': [19.4, 19.9, 19.8, 19.5, 22.2, 20.9, 24.6, 23.6, 23.5, 19.4, 21.3, 19.3, 22.1, 21.3, 22.3, 22.1, 21.7, 20.1, 19.6, 23.7, 2.3, 24.7, 23.8, 21.6, 18.8, 20.5, 20.5, 21.5, 18.2, 24.9, 23.2, 20.0, 23.9, 19.3, 20.6, 22.0, 19.6, 21.7, 23.3, 23.4, 18.9, 22.0, 19.9, 20.9, 20.6, 23.2, 23.5, 22.0, 20.5, 20.9, 20.6]}\n" ] } ], "source": [ "print (dict_col(df_sat))\n", "print (\"\")\n", "print (dict_col(df_act))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 9. Merge the dataframes on the state column." ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [], "source": [ "df_total = pd.merge(df_sat, df_act, on='State')" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipation_xEBRWMath_xParticipation_yEnglishMath_yReadingScience
0Alabama5.0593572100.018.918.419.719.4
1Alaska38.054753365.018.719.820.419.9
2Arizona30.056355362.018.619.820.119.8
3Arkansas3.0614594100.018.919.019.719.5
4California53.053152431.022.522.723.122.2
\n", "
" ], "text/plain": [ " State Participation_x EBRW Math_x Participation_y English \\\n", "0 Alabama 5.0 593 572 100.0 18.9 \n", "1 Alaska 38.0 547 533 65.0 18.7 \n", "2 Arizona 30.0 563 553 62.0 18.6 \n", "3 Arkansas 3.0 614 594 100.0 18.9 \n", "4 California 53.0 531 524 31.0 22.5 \n", "\n", " Math_y Reading Science \n", "0 18.4 19.7 19.4 \n", "1 19.8 20.4 19.9 \n", "2 19.8 20.1 19.8 \n", "3 19.0 19.7 19.5 \n", "4 22.7 23.1 22.2 " ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 10. Change the names of the columns so you can distinguish between the SAT columns and the ACT columns." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StateParticipation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
0Alabama5.0593572100.018.918.419.719.4
1Alaska38.054753365.018.719.820.419.9
2Arizona30.056355362.018.619.820.119.8
\n", "
" ], "text/plain": [ " State Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "0 Alabama 5.0 593 572 100.0 \n", "1 Alaska 38.0 547 533 65.0 \n", "2 Arizona 30.0 563 553 62.0 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "0 18.9 18.4 19.7 19.4 \n", "1 18.7 19.8 20.4 19.9 \n", "2 18.6 19.8 20.1 19.8 " ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total = pd.merge(df_sat, df_act, on='State')\n", "df_total.columns = ['State','Participation_SAT (%)','EBRW_SAT','Math_SAT',\\\n", " 'Participation_ACT (%)','English_ACT','Math_ACT','Reading_ACT','Science_ACT']\n", "df_total.head(3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 11. Print the minimum and maximum of each numeric column in the data frame." ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
min2.0482.052.08.016.318.018.12.3
max100.0644.0651.0100.025.525.326.024.9
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "min 2.0 482.0 52.0 8.0 \n", "max 100.0 644.0 651.0 100.0 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "min 16.3 18.0 18.1 2.3 \n", "max 25.5 25.3 26.0 24.9 " ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total.describe().loc[['min','max']]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 12. Write a function using only list comprehensions, no loops, to compute standard deviation. Using this function, calculate the standard deviation of each numeric column in both data sets. Add these to a list called `sd`.\n", "\n", "$$\\sigma = \\sqrt{\\frac{1}{n}\\sum_{i=1}^n(x_i - \\mu)^2}$$" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "def stdev(X):\n", " n = len(X)\n", " return ((1.0/n)*np.sum([(x-np.mean(X))**2 for x in X]))**(0.5)" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[34.929, 45.217, 84.073, 31.824, 2.33, 1.962, 2.047, 3.151]\n" ] } ], "source": [ "cols = df_total.columns[1:].tolist()\n", "sd = [round( stdev([df_total[col].tolist() for col in cols][i] ) ,3) for i in range(0,len(cols))]\n", "print (sd)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Note that Pandas calculates `std` DataFrame using $n-1$ as denominator instead of $n$:" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
std35.27663245.66690184.90911932.1408422.3536771.9819892.0672713.182463
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "std 35.276632 45.666901 84.909119 32.140842 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "std 2.353677 1.981989 2.067271 3.182463 " ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total.describe().loc[['std']]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Setting the number of ${\\rm{ddof}}=0$ solves this issue and we obtain the same values as the list `sd`." ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Participation_SAT (%) 34.929071\n", "EBRW_SAT 45.216970\n", "Math_SAT 84.072555\n", "Participation_ACT (%) 31.824176\n", "English_ACT 2.330488\n", "Math_ACT 1.962462\n", "Reading_ACT 2.046903\n", "Science_ACT 3.151108\n", "dtype: float64" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total.std(ddof=0)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Step 2: Manipulate the dataframe" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 13. Turn the list `sd` into a new observation in your dataset.\n", "\n", "I first put `State` as index and then concatenate the new row, renaming it." ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
State
Alabama5.0593572100.018.918.419.719.4
Alaska38.054753365.018.719.820.419.9
Arizona30.056355362.018.619.820.119.8
Arkansas3.0614594100.018.919.019.719.5
California53.053152431.022.522.723.122.2
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "State \n", "Alabama 5.0 593 572 100.0 \n", "Alaska 38.0 547 533 65.0 \n", "Arizona 30.0 563 553 62.0 \n", "Arkansas 3.0 614 594 100.0 \n", "California 53.0 531 524 31.0 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "State \n", "Alabama 18.9 18.4 19.7 19.4 \n", "Alaska 18.7 19.8 20.4 19.9 \n", "Arizona 18.6 19.8 20.1 19.8 \n", "Arkansas 18.9 19.0 19.7 19.5 \n", "California 22.5 22.7 23.1 22.2 " ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new = df_total.copy()\n", "df_total_new = df_total_new.set_index('State')\n", "df_total_new.head()" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [], "source": [ "df2 = pd.DataFrame([[34.929, 45.217, 84.073, 31.824, 2.33, 1.962, 2.047, 3.151]],columns=df_total_new.columns)\n", "df_total_new = pd.concat([df2,df_total_new])" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
sd34.92945.21784.07331.8242.331.9622.0473.151
Alabama5.000593.000572.000100.00018.9018.40019.70019.400
Alaska38.000547.000533.00065.00018.7019.80020.40019.900
Arizona30.000563.000553.00062.00018.6019.80020.10019.800
Arkansas3.000614.000594.000100.00018.9019.00019.70019.500
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "sd 34.929 45.217 84.073 31.824 \n", "Alabama 5.000 593.000 572.000 100.000 \n", "Alaska 38.000 547.000 533.000 65.000 \n", "Arizona 30.000 563.000 553.000 62.000 \n", "Arkansas 3.000 614.000 594.000 100.000 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "sd 2.33 1.962 2.047 3.151 \n", "Alabama 18.90 18.400 19.700 19.400 \n", "Alaska 18.70 19.800 20.400 19.900 \n", "Arizona 18.60 19.800 20.100 19.800 \n", "Arkansas 18.90 19.000 19.700 19.500 " ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new = df_total_new.rename(index={df_total_new.index[0]: 'sd'})\n", "df_total_new.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 14. Sort the dataframe by the values in a numeric column (e.g. observations descending by SAT participation rate)\n", "\n", "I will start from the DataFrame without the `sd` and include it afterwards:" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
sd34.92945.21784.07331.8242.331.9622.0473.151
District of Columbia100.000482.000468.00032.00024.4023.50024.90023.500
Michigan100.000509.000495.00029.00024.1023.70024.50023.800
Connecticut100.000530.000512.00031.00025.5024.60025.60024.600
Delaware100.000503.000492.00018.00024.1023.40024.80023.600
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT \\\n", "sd 34.929 45.217 84.073 \n", "District of Columbia 100.000 482.000 468.000 \n", "Michigan 100.000 509.000 495.000 \n", "Connecticut 100.000 530.000 512.000 \n", "Delaware 100.000 503.000 492.000 \n", "\n", " Participation_ACT (%) English_ACT Math_ACT \\\n", "sd 31.824 2.33 1.962 \n", "District of Columbia 32.000 24.40 23.500 \n", "Michigan 29.000 24.10 23.700 \n", "Connecticut 31.000 25.50 24.600 \n", "Delaware 18.000 24.10 23.400 \n", "\n", " Reading_ACT Science_ACT \n", "sd 2.047 3.151 \n", "District of Columbia 24.900 23.500 \n", "Michigan 24.500 23.800 \n", "Connecticut 25.600 24.600 \n", "Delaware 24.800 23.600 " ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new = df_total.copy() \n", "df_total_new = df_total_new.set_index('State').sort_values(\"Participation_SAT (%)\",ascending=False)\n", "df_total_new = pd.concat([df2,df_total_new])\n", "df_total_new = df_total_new.rename(index={df_total_new.index[0]: 'sd'})\n", "\n", "df_total_new.head()" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)
sd34.929
District of Columbia100.000
Michigan100.000
Connecticut100.000
Delaware100.000
New Hampshire96.000
Maine95.000
Idaho93.000
Florida83.000
Massachusetts76.000
Rhode Island71.000
New Jersey70.000
Maryland69.000
New York67.000
Virginia65.000
Pennsylvania65.000
Washington64.000
Indiana63.000
Texas62.000
Georgia61.000
\n", "
" ], "text/plain": [ " Participation_SAT (%)\n", "sd 34.929\n", "District of Columbia 100.000\n", "Michigan 100.000\n", "Connecticut 100.000\n", "Delaware 100.000\n", "New Hampshire 96.000\n", "Maine 95.000\n", "Idaho 93.000\n", "Florida 83.000\n", "Massachusetts 76.000\n", "Rhode Island 71.000\n", "New Jersey 70.000\n", "Maryland 69.000\n", "New York 67.000\n", "Virginia 65.000\n", "Pennsylvania 65.000\n", "Washington 64.000\n", "Indiana 63.000\n", "Texas 62.000\n", "Georgia 61.000" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new[['Participation_SAT (%)']].head(20)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 15. Use a boolean filter to display only observations with a score above a certain threshold (e.g. only states with a participation rate above 50%)\n", "\n", "I printed out the tail to check." ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
Texas62.0513.0507.045.019.520.721.120.9
Georgia61.0535.0515.055.021.020.922.021.3
Vermont60.0562.0551.029.023.323.124.423.2
Hawaii55.0544.0541.090.017.819.219.219.3
California53.0531.0524.031.022.522.723.122.2
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "Texas 62.0 513.0 507.0 45.0 \n", "Georgia 61.0 535.0 515.0 55.0 \n", "Vermont 60.0 562.0 551.0 29.0 \n", "Hawaii 55.0 544.0 541.0 90.0 \n", "California 53.0 531.0 524.0 31.0 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "Texas 19.5 20.7 21.1 20.9 \n", "Georgia 21.0 20.9 22.0 21.3 \n", "Vermont 23.3 23.1 24.4 23.2 \n", "Hawaii 17.8 19.2 19.2 19.3 \n", "California 22.5 22.7 23.1 22.2 " ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new = df_total_new[df_total_new['Participation_SAT (%)']>50]\n", "df_total_new.tail()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Step 3: Visualize the data" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "#### 16. Using MatPlotLib and PyPlot, plot the distribution of the Rate columns for both SAT and ACT using histograms. (You should have two histograms. You might find [this link](https://matplotlib.org/users/pyplot_tutorial.html#working-with-multiple-figures-and-axes) helpful in organizing one plot above the other.) \n", "\n", "There are certain technical criteria for the optimal choice of number of bins which will not be used here but are briefly described in the end of the notebook. We will follow the heuristical \"not too large, not too little\" bin size criterion.\n", "\n", "There is an outlier which we will exclude now for good measure:" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [], "source": [ "df_total_new = df_total_new[df_total_new.index != 'Maryland']" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "p1 = df_total_new[['Participation_SAT (%)']]\n", "p2 = df_total_new[['Participation_ACT (%)']]\n", "\n", "fig, axes = plt.subplots(1, 2)\n", "p1.hist('Participation_SAT (%)', bins=10, ax=axes[0])\n", "p2.hist('Participation_ACT (%)', bins=10, ax=axes[1])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 17. Plot the Math(s) distributions from both data sets." ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "p1 = df_total_new[['Math_SAT']]\n", "p2 = df_total_new[['Math_ACT']]\n", "\n", "fig, axes = plt.subplots(1, 2)\n", "\n", "p1.hist('Math_SAT', bins=10, ax=axes[0])\n", "p2.hist('Math_ACT', bins=10, ax=axes[1])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 18. Plot the Verbal distributions from both data sets.\n", "\n", "In the ACT scores I joined English and reading into one Verbal section following SAT's strategy:" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACTVerbal_ACT
District of Columbia100.0482.0468.032.024.423.524.923.524.65
Michigan100.0509.0495.029.024.123.724.523.824.30
Connecticut100.0530.0512.031.025.524.625.624.625.55
Delaware100.0503.0492.018.024.123.424.823.624.45
New Hampshire96.0532.0520.018.025.425.126.024.925.70
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT \\\n", "District of Columbia 100.0 482.0 468.0 \n", "Michigan 100.0 509.0 495.0 \n", "Connecticut 100.0 530.0 512.0 \n", "Delaware 100.0 503.0 492.0 \n", "New Hampshire 96.0 532.0 520.0 \n", "\n", " Participation_ACT (%) English_ACT Math_ACT \\\n", "District of Columbia 32.0 24.4 23.5 \n", "Michigan 29.0 24.1 23.7 \n", "Connecticut 31.0 25.5 24.6 \n", "Delaware 18.0 24.1 23.4 \n", "New Hampshire 18.0 25.4 25.1 \n", "\n", " Reading_ACT Science_ACT Verbal_ACT \n", "District of Columbia 24.9 23.5 24.65 \n", "Michigan 24.5 23.8 24.30 \n", "Connecticut 25.6 24.6 25.55 \n", "Delaware 24.8 23.6 24.45 \n", "New Hampshire 26.0 24.9 25.70 " ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_total_new['Verbal_ACT'] = (df_total_new['English_ACT'] + df_total_new['Reading_ACT'])/2\n", "df_total_new.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next I change syntax and disposition of plots to make the x-axis labels more legible" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[],\n", " []],\n", " dtype=object)" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "columns = ['EBRW_SAT','Verbal_ACT']\n", "df_total_new.hist(column=columns, layout=(2,1))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can do other plots using seaborn as well." ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['Participation_SAT (%)', 'EBRW_SAT', 'Math_SAT', 'Participation_ACT (%)', 'English_ACT', 'Math_ACT', 'Reading_ACT', 'Science_ACT', 'Verbal_ACT']\n" ] } ], "source": [ "print( df_total_new.columns.tolist())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 1) New ones:" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAABCwAAAQtCAYAAACRTt41AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzs3X2UnNldH/hvdVdVuzU9tpBQTtbnmCgi+CYbWISgYys49myI47CQcJbsEsU7G2JCznBiODJhIcF2As4byQGH1Z511hNe4rAiCBYvySa7g+ckvBkisEAWG5JwHZC1kIVNbCmDp2dEV3er9w+17JZGXWq1uqpuV30+5/io++lW1e+5VfNzPV89997O5uZmAAAAAFoyN+kCAAAAAO4lsAAAAACaI7AAAAAAmiOwAAAAAJojsAAAAACaI7AAAAAAmtOddAEP8rGPPT9z+64uLS1kZWV10mWM3Syet3OeHftx3seOPd7Zp3J29DA9t7XXUj3DqWc49Qw3i/W01nMPutbeQ60wLi9lTO5v2sdlp57rDosGdbvzky5hImbxvJ3z7JjG827tnNQznHqGU89w6uFRec3uz7i8lDG5v1kdF4EFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0JzuqB64lPKaJH+n1vpEKeX3JHlfks0kv5TkrbXWW6WUb0nyJUnWk7yt1vqhUdUDwOj1+/Pp9LpZWuxl5eZaNtfWMxhsTLqsJo1qrLwGD+fOeM1357Lw2ILx4sDw3/r+2u14ztK4z9K50q6RBBallG9K8t8neWHr0N9N8s5a60+UUt6b5MtKKf9PkjckeU2SVyV5f5LlUdQzS5bf/VNjf85L3/D6sT8nPIpJ/Hfy7/76Hxv7c45bvz+f1c5czp6/nEvXbmT5+JGcO3MyC/34gHOPUY3VsMflpbxnOai8d/fXbsdzlsZ9ls6Vto1qSsivJvnybd9/fpKf3Pr6mSR/JMnrkjxba92stf5akm4p5diI6gFgxDq9bs5euJKLV69n/dZmLl69nrMXrqTTG9nNfAfWqMbKa/BwjBcHlffu/trteM7SuM/SudK2kbzjaq3vL6Uc33aoU2vd3Pr6+SSvSPLyJNe3/c6d4x/b/lhLSwvpdudHUWaz5ufncvjwoUmXsWv7VetBO+/94Jxnx0E574fpufee03x3Lpeu3bjrdy5du5GlxV4We6Pv462N8bB6RjVWwx43m/vXr/dDC6/XpN+zw7QwPtupZzT2+jm35ffuTlp+zXY7nqMY91bHZZLvsVbHZNJmdVzGFZHd2vb140meS/KJra/vPX6XlZXV0VbWoMOHD+W5516cdBm7tl+1HrTz3g/OeXZsbNx65PM+duzxB//SI3qYnnvva7nw2EKWjx/JxaufyqKXjx/Jys21rL4w+l7e2ntrWD2jGqthj7vYmz8w4zMuk37PDtPC+Gw3i/W01nO3a/m9u5PW3kPb7XY8RzHurY7LJN9jrY7JpE37uOzUc8e1S8iHSylPbH39xUk+mORnkryplDJXSvmMJHO11o+PqR4A9tnm2nrOnTmZ0yeOpjvXyekTR3PuzMlsrq1PurTmjGqsvAYPx3hxUHnv7q/djucsjfssnSttG9cdFt+Q5LtKKf0k/zbJD9daN0opH0xyMbeDk7eOqRYARmAw2MhCP3n6yVNWFH+AUY3VsMc9NHt3kT6Q9ywHlffu/trteM7SuM/SudK2kQUWtdZrSV679fVHcntHkHt/51uTfOuoagBgvAaDjWSw0ewtyS0Z1Vh5DR7OnfFa7M0bMw4U/63vr92O5yyN+yydK+0a15QQAAAAgF0TWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADN6U66AACAFvX78+n0ulla7GXl5lo219YzGGxMuiyAqXSn585357Lw2IKeSxKBBQDAS/T781ntzOXs+cu5dO1Glo8fybkzJ7PQjw/QAPtMz2UnpoQAANyj0+vm7IUruXj1etZvbebi1es5e+FKOj3/1gOw3/RcdiKwAAC4x9JiL5eu3bjr2KVrN7K02JtQRQDTS89lJwILAIB7rNxcy/LxI3cdWz5+JCs31yZUEcD00nPZicACAOAem2vrOXfmZE6fOJruXCenTxzNuTMns7m2PunSAKaOnstOTAoCAJLYFWO7wWAjC/3k6SdPGQ/gkemvw+m57ERgAQBYof0+BoONZLCR1RdWJ10KcIAN6698yp2eu9ib13f5JFNCAAArtAOMiP4KeyewAACs0A4wIvor7J3AAgCwQjvAiOivsHcCCwDACu0AI6K/wt6ZOAUAWKEdYESG9ddDhyZdHbRNYAEAJLErBsCo6K+wN6aEAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNsUsIAJAk6ffn0+l1bWsKzDS9ENohsAAA0u/PZ7Uzl7PnL+fStRtZPn4k586czEI/PqgDM0MvhLaYEgIApNPr5uyFK7l49XrWb23m4tXrOXvhSjo9/7YBzA69ENoisAAAsrTYy6VrN+46dunajSwt9iZUEcD46YXQFoEFAJCVm2tZPn7krmPLx49k5ebahCoCGD+9ENoisAAAsrm2nnNnTub0iaPpznVy+sTRnDtzMptr65MuDWBs9EJoi8lYAEAGg40s9JOnnzxlZXxgZumF0BaBBQCQZGsF/MFGVl9YnXQpABOjF0I7TAkBAAAAmiOwAAAAAJojsAAAAACaI7AAAAAAmiOwAAAAAJojsAAAAACaI7AAAAAAmiOwAAAAAJojsAAAAACaI7AAAAAAmtMd1xOVUhaS/IMkJ5J8IslbkxxNci7JepJna63vGlc9AAAAQLvGeYfFn0+yUmt9bZKvS/I/J3lvkjcneV2S15RSTo2xHgAAAKBR4wws/vMkzyRJrbUmWU6yUGv91VrrZpIPJPmiMdYDAAAANGpsU0KSXEnypaWUf5zkNUlekeRXt/38+dyeLnKXpaWFdLvz46mwEfPzczl8+NCky9i1/ar1oJ33fnDOs+OgnPfD9NzWzkk9w6lnOPUMp57RmKXPudPymu034/JSxuT+ZnVcxhlYfG+S35fkx5P8TJJfTPLYtp8/nuS5e//SysrqWIpryeHDh/Lccy9Ouoxd269aD9p57wfnPDs2Nm498nkfO/b4PlWzs4fpua29luoZTj3DqWe4WayntZ570LX2HmqFcXkpY3J/0z4uO/XccU4JWU7y07XWJ5L8SJKPJBmUUj6zlNJJ8qYkHxxjPQAAAECjxnmHxb9L8tdLKf9Dbt9J8eeSfEaS708yn9u7hPzcGOsBAAAAGjW2wKLW+vEkf+Sew7+R5LXjqgEAAAA4GMY5JQQAAABgVwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHO6D/qFUspnJ3kiydEk/zHJv6i1fmTEdQEAAAAzbMfAopTy+5J8e5KbSf5Vkt9I8mlJvq2U0k3y9lrrvx5LlQAAAMBMGXaHxZkk/12t9bfu/UEp5dOSfH2SvzqqwgAAAIDZtWNgUWv9liE/+08RVgAAAAAj8sA1LJKklPLaJH8lyaEk31NrPT/SqgCAqdTvz6fT62a+O5eFxxayubaewWBj0mUBPLI7/W1psZeVm2v6G+yDHXcJKaV8xrZv/0ySP57ki5L8hVEXBQBMn35/PquduTx1/nJe/Y5n8tT5y1ntzKXfn590aQCPRH+D0Ri2rek3llL+Rinl8SS/mOSHk7w/yf89lsoAgKnS6XVz9sKVXLx6Peu3NnPx6vWcvXAlnd6ubvgEaJb+BqMxbA2LryulfE6S/yXJzyR5S5JOrfW5cRUHAEyPpcVeLl27cdexS9duZGmxl9UXVidUFcCj099gNIbdYXHn5+9Kci3Jdyf5wlEXBABMp5Wba1k+fuSuY8vHj2Tl5tqEKgLYH/objMawNSx+KLfvqvimJCeT/Kkkryql/MCYagMApsjm2nrOnTmZ0yeOpjvXyekTR3PuzMlsrq1PujSAR6K/wWgMm1T1u5J8dZKlJP9TrfVWkveWUr5/LJUBAFNlMNjIQj95+slTVtEHpor+BqMxLLD4q0n+1yTPJ3nnnYO11udHXRQAMJ0Gg41ksJHF3rx53cBUudPf9DbYP8MCiw/WWj+w0w9LKYdqrS+OoCYAAABgxg0LLN5TSvn5JBdqrdfvHCylfHqSJ5N8XpKvHHF9AAAAwAwatq3pW0opX5HkH5dSXpXk40keT/L/Jfl7tdb/cUw1AgAAADNm2B0WqbX+UJIfKqW8LMmnJbleax2MpTIAAABgZg0NLO6otf52kt8ccS0AAAAASZK5SRcAAAAAcK8dA4tSyueNsxAAAACAO4bdYfHusVUBAAAAsI0pIQAAAEBzhi26+YWllN+451gnyWat9ZUjrAkAAACYccMCi39Za/0vx1YJAAAAwJZdbWu6H0opvST/MMnxJBtJ/nyS9STvS7KZ5JeSvLXWemtcNQEAAABtGhZY/M37HSylvLbW+rN7eK7/Kkm31voHSylv3Hr8XpJ31lp/opTy3iRfluRH9vDYTVp+909NugQAAAA4kHYMLGqt//zO16WUhSRvTvK1SRaSfPYenusjSbqllLkkL0+yluS1SX5y6+fPJPmjmaLAAgAAANiboVNCSinHk7w1yZ/K7QU3/1St9V/u8blWcns6yC8n+fQkX5rk9bXWza2fP5/kFff+paWlhXS783t8Ssbh8OFD+/I48/Nz+/ZYB4Vznh0H5bwfpue2dk7qGU49w6lnOPWMxix9zp2W12y/GZeXMib3N6vjsmNgUUr5J0k+Lcn35fYdFT/4CGFFknx9kg/UWr+5lPKqJD+WpL/t548nee7ev7SysvoIT8k4PPfci/vyOIcPH9q3xzoonPPs2Ni49cjnfezY4/tUzc4epue29lqqZzj1DKee4WaxntZ67kHX2nuoFcblpYzJ/U37uOzUc+eG/J1Obk/bWNz6vc0hv7sb/ynJb219fSO316/4cCnlia1jX5zkg4/4HAAAAMAU2DGwqLX+iSRfmeRIkp9L8rmllD+2tQbFXnxnklOllA/m9t0Vb8/t6SbvKqVczO27LX54j48NAAAATJGha1jUWv99bgcKfy3Jm5J8dZK/n+QzHvaJaq0rSb7iPj96w8M+FgAAADDddnW3xNbCmL+e5JuTfP5IKwIAAABm3rBFN9+Y5HuSfGaSP5fkG5N8LMl3bR0HAAAAGIlhd1h8Y5LX1FrXkvyl3J4S8obcnhYCAAAAMDLD1rDYrLX+ZinlRJK1WuuvJEkpZX08pQEAAACzatgdFt1SSjfJlyT5QJKUUg4neWwchQEAAACza9gdFv8wyb9NMp/kj5RSPjvJ9yc5N47CAAAAgNm14x0Wtdbvy+0dQX5PrfVqkutJ/myt9XuTpJTyu8ZTIgAAADBrht1hkVrrJ7Z9/ZtJfnPbj/9Bkj88oroAAACAGTZsDYsH6exbFQAAAADbPEpgsblvVQAAAABs8yiBBQAAAMBImBICAAAANOdRAosf27cqAAAAALYZuktIkpRS3pjkLyZZuHOs1vqHa61/fZSFAQAAALPrgYFFku9M8rYkvz7iWgAAAACS7C6w+LVa6z8feSUAAAAAW3YTWPzHUsp7k3w4W1uZ1lr//kirAgAAAGbabgKLj279+TtHWQgAANOp359Pp9fN0mIvKzfXsrm2nsFgY9JlAbBH4+rrD9wlpNb6riQ/n+Rmkitb3wMAwAP1+/NZ7czlqfOX8+p3PJOnzl/Oamcu/f78pEsDYA/G2dcfGFiUUr4tyVuSDJJ8ZSnlO/a9CgAAplKn183ZC1dy8er1rN/azMWr13P2wpV0eru50ReA1oyzr+/mEV9fa/3CJCmlnEvys/teBQAAU2lpsZdL127cdezStRtZWuxl9YXVCVUFwF6Ns68/8A6LJL1Syp3f62Rr4U0AAHiQlZtrWT5+5K5jy8ePZOXm2oQqAuBRjLOv7yaw+MEkP1NK+c4kP731PQAAPNDm2nrOnTmZ0yeOpjvXyekTR3PuzMlsrq1PujQA9mCcff2BU0Jqre8upXwgye9N8j211l/a9yoAAJhKg8FGFvrJ00+esksIwBQYZ1/fMbAopXx1rfW7txbdvDMN5FQpJbXWt+97JQAATKXBYCMZbFizAmBKjKuvD7vD4te3/vzle45bwwIAAAAYqR0Di1rrB7a+XK61fu2d46WU70vyfaMuDAAAAJhdw6aEvDXJO5N8Winly7cOd5L8m3EUBgAAAMyuYXdYvCfJe0opb6+1/q0x1gQAAADMuAfuEpLkvaWUP52kl9t3WLyy1vptoy0LAAAAmGW7CSx+OMlHkvwXSW4meXGkFQEAAAAzb243v1Rr/Zrc3i3kjUk+baQVAQAAADNvV4FFKeVlSR7L7S1Nl0ZaEQAAADDzdhNYvCfJ1yd5Nsmv5/adFgAAAAAj88A1LGqt7y+lzCU5luR/q7V+YvRlAQAAALPsgXdYlFK+PMnVJD+a5HIp5Y0jrwoAAACYabuZEvJXkvyBWuvnJfnCJH9ztCUBAAAAs243gcX1Wut/TJJa639IYkoIAAAAMFIPXMMiySdKKR9I8pNJviDJoVLK30qSWuvbR1kcAAAAMJt2E1j8k21f/7+jKgQAAADgjh0Di1LKF9Rafz7Jb977s1rrsyOtCgAAAJhpw+6w+KIkP5/kTyfZTNLZ+jNJBBYAAADAyOy46Gat9e9sffmNSX6g1vqWJJeT/MVxFAYAAADMrt3sEvIDSV6x9fWNJOdHVw4AAADA7gKLx2qtP5wktdZ/lOSx0ZYEAAAAzLrd7BIyKKW8McnPJvkDSTZGWxIAAAAw63Zzh8VXJ3lrkg8l+QtJnhppRQAAAMDMG7atabfWup7k15J8Re7eJQQAAABgZIZNCfm+JG9OUvOpoOJOaHFixHUBAEy9fn8+nV43S4u9rNxcy+baegYDs28BdksfnW47Bha11jdvffkVtdZLd46XUp4YdVEAANOu35/PamcuZ89fzqVrN7J8/EjOnTmZhf6kKwM4GIb1UaHFdBg2JeR1SX5/kq8vpfzdrcNzSb42yWePoTYAgKnV6XVz9vzlXLx6PUly8er1nL1wJU8/eWrClQEcDEP7qMBiKgybEvJckt+ZZCHJf7Z17FaSbxp1UQAA025psZdL127cdezStRtZWuxlY/3WhKoCODiG9dHVF1YnVBX7adiUkF9K8kullM1a618bY00AAFNv5eZalo8f+eS/DCbJ8vEjWbm5lsXe/AQrAzgYhvVRpsNutjV9opTi/zUBAPbR5tp6zp05mdMnjqY718npE0dz7szJbK6tT7o0gANBH51+w6aE3HEsyW+UUj6a2zuEbNZa/+DDPlEp5c8m+bNb374syckkTyQ5l2Q9ybO11nc97OMCABxEg8FGFvrJ00+eesnq9ocOTbo6gPYN66NMh90EFl+6H09Ua31fkvclSSnlPUm+N8l7k/zJJFeT/J+llFO11sv78XwAAA9yZzu8+e5cFh5bGPsH3cFgIxlsmGsNsEfD+qgtTw++3QQWvST/7dafnSSvTPLUXp+wlPIFub37yDcn+fpa669uHf9Aki9KMpLAYvndPzWKhyWTGdtL3/D6sT8no+G/TWBSbIcHML30+OmwmzUsvm/rz9cl+d1Jjj7ic749ybuSvDzJJ7Ydfz7JKx7xsQEAdqXT6+bshSu5ePV61m9tfnI7vE5vN/+eA0DL9PjpsJtX68Va67eVUj6r1vpVpZQP7vXJSimHk/zeWuuPl1JenuTxbT9+PLe3Ur3L0tJCul1rfnK3w4enY3Lv/Pzc1JzLbs3iOScH57wfpue2dk7qGU4996mhO7fjdniT3qWjhfHZTj2jMUufc6flNdtvxuWl9mtMWu7xezGr75XdBBadUsrvTLJUSnksyZFHeL7XJ/nnSVJr/UQpZVBK+czcXsPiTbl958VdVlbM6eSlnnvuxUmXsC8OHz40NeeyW7N4zkmysXHrkc/72LHHH/xLj+hhem5rr6V6hlPPSy08trDjdniTXlOihfHZbhbraa3nHnStvYdaYVxear/GpOUevxfT/l7ZqefuZkrIu5L810nOJ/lokmceoY6S2+HEHV+T5PuTfCjJh2utP/cIjw0AsGu2wwOYXnr8dBh6h8XWtI2fr7XeWRXvdzzKk9Vav/2e7382yWsf5TEBAPbCdngA00uPnw473mFRSvnaJL+Y5BdLKW8aX0kAAOMx2NoKb2P9VlZfWPVBFmCK3Onx1z++oscfUMOmhLw5t6dwnE7ytvGUAwAAADA8sPjtWuug1vrxJP1xFQQAAACwm0U3k6Qz0ioAAAAAthm26ObvL6X8o9wOK+58nSSptb555JUBAAAAM2tYYPEV275+76gLAQAAALhjx8Ci1vqT4ywEAAAA4I7drmEBAAAAMDYCCwAAAKA5AgsAAACgOQILAAAAoDnDdgkBADjw+v35dHrdLC32snJzLZtr6xkMNiZdFgB7oKfPFoEFADC1+v35rHbmcvb85Vy6diPLx4/k3JmTWejHB1yAA0ZPnz2mhAAAU6vT6+bshSu5ePV61m9t5uLV6zl74Uo6Pf9mA3DQ6OmzR2ABAEytpcVeLl27cdexS9duZGmxN6GKANgrPX32CCwAgKm1cnMty8eP3HVs+fiRrNxcm1BFAOyVnj57BBYAwNTaXFvPuTMnc/rE0XTnOjl94mjOnTmZzbX1SZcGwEPS02ePyT4AwNQaDDay0E+efvKUFeUBDjg9ffYILACAqTYYbCSDjay+sDrpUgB4RHr6bDElBAAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojl1CAAAa0e/Pp9PrZr47l4XHFmzX9wB3xsv2hsCotNRnWqplXAQWAAAN6Pfns9qZy9nzl3Pp2o0sHz+Sc2dOZqGfqf9AuhfGCxi11vpMS7WMiykhAAAN6PS6OXvhSi5evZ71W5u5ePV6zl64kk7Pvy/dj/ECRq2lPrO6cauZWsZJYAEA0IClxV4uXbtx17FL125kabE3oYraZryAUWupzxxa6DZTyzgJLAAAGrBycy3Lx4/cdWz5+JGs3FybUEVtM17AqLXUZ15cXW+mlnESWAAANGBzbT3nzpzM6RNH053r5PSJozl35mQ219YnXVqTjBcwai31mYX5uWZqGafpnvACAHBADAYbWegnTz956pMrwM9t3sqtTjdHX744MyvC79b9xsv4APvpYfvMqHfxWNi8NXM9T2ABANCIwWAjGWxksTefzbX1vNiZy9kLs7Ui/MO4M16rL6xOuhRgSu22z4xjR5FZ7HmmhAAANKil1ekBGE7PHg2BBQBAg1panR6A4fTs0RBYAAA0qKXV6QEYTs8eDYEFAECDWlqdHoDh9OzRMKEGAKBB965Of3N1PRubydLLFmZmdXiA1uy0E4idi0ZDYAEA0Kg7K8Jvrq3fXn3+whU7hgBMyIN2ApnFXTxGzZQQAIDGWX0eYPL04vETWAAANM7q8wCTpxePn8ACAKBxVp8HmDy9ePwEFgAAjbP6PMDk6cXjZ7INAEDjrD4PMHl68fgJLACAJDtv1UYbrD4P7JZ+Pjp68XgJLACAB27VBsDBoJ8zTaxhAQDYqg1gSujnTBOBBQBgqzaAKaGfM00EFgCArdoApoR+zjQRWAAAtmoDmBL6OdPERCYAwFZtj8iK/EArJtHP9UBGRWABACSxVdteWZEfaM04+7keyCiZEgIA8AisyA/MMj2QURJYAAA8AivyA7NMD2SUBBYAAI/AivzALNMDGSWBBQDAI7AiPzDL9EBGaawTi0op35zkTyTpJ/l7SX4yyfuSbCb5pSRvrbXeGmdNAACPwg4rbbBLAUyGHjibxtVzx3aHRSnliSR/MMkXJnlDklcl+btJ3llr/UNJOkm+bFz1AADsl8HWavzXP76S1RdWfVAfszu7FDx1/nJe/Y5n8tT5y1ntzKXfn590aTAT9MDZMs6eO847LN6U5F8l+ZEkL0/yjUn+fG7fZZEkzyT5o1s/h6GW3/1TY32+S9/w+rE+XzL+c0wmc54A8Kg6vW7Onr+ci1evJ8kndyl4+slTiQsngH01zp47zsDi05P8riRfmuR3J/k/kszVWje3fv58klfc+5eWlhbS7UrHmazDhw+N5HHn5+dG9th7MY5aWjvncTko5/0wPbe1c1LPcOoZTj3DtV7PfHdux10KFnvtfo6cpc+5rb2HWmFcXsqY3F9L4zLOnjvOwOJ6kl+utQ6S1FLKb+f2tJA7Hk/y3L1/aWVldUzlwc6ee+7FkTzu4cOHRvbYezGOWlo753HZ2Lj1yOd97Njj+1TNzh6m57b2WqpnOPUMp57hWq9n4bGFLB8/8sl/7Us+tUvB6gt7+yzZWs896Fp7D7XCuLyUMbm/lsZlnD13nLuE/HSSP1ZK6ZRSXpnksST/YmttiyT54iQfHGM9AABMAbsUAIzPOHvu2O6wqLX+s1LK65N8KLeDkrcm+WiS7yql9JP82yQ/PK56AACYDnYpABifcfbcsW5rWmv9pvscfsM4awAAYPoMBhvJ1k4FAIzWuHruOKeEAAAAAOyKwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiRQWCUAAAgAElEQVSOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI7AAgAAAGiOwAIAAABoTnfSBQAA8Gj6/fl0et0sLfaycnMtm2vrGQw2Jl0WAPtoFnu9wAIA4ADr9+ez2pnL2fOXc+najSwfP5JzZ05moZ+p/yALMEtmsdebEgIAcIB1et2cvXAlF69ez/qtzVy8ej1nL1xJp+ffpQCmxerGrZns9QILAIADbGmxl0vXbtx17NK1G1la7E2oIgD226GF7kz2eoEFAMABtnJzLcvHj9x1bPn4kazcXJtQRQDstxdX12ey1wssAAAOsM219Zw7czKnTxxNd66T0yeO5tyZk9lcW590aQDsk4X5uZns9dM94QUAYMoNBhtZ6CdPP3lqplaOB5g1C5u3Zq7XCywAAA64wWAjGWxk9YXVSZcCwIjMYq83JQQAAABojsACAAAAaI7AAgAAAGiOwAIAAABojsACAAAAaI5dQgAAkvT78+n0ujO1XRzAQad3TzeBBQBAktXOXM6ev5xL125k+fiRnDtzMgv9+OAL0Kh+f17vnnKmhAAAM29141bOXriSi1evZ/3WZi5evZ6zF66k0/NvOwCt6vS6eveUE1gAADPv0EI3l67duOvYpWs3srTYm1BFADzI0mJP755yAgsAYOa9uLqe5eNH7jq2fPxIVm6uTagiAB5k5eaa3j3lBBYAwMxbmJ/LuTMnc/rE0XTnOjl94mjOnTmZzbX1SZcGwA4219b17ilncg8AQJKFzVt5+slTVpoHOCAGg40s9KN3TzGBBQBAtlaUH2xk9YXVSZcCwC7p3dPNlBAAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOZ3Nzc1J1wAAAABwF3dYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM0RWAAAAADNEVgAAAAAzRFYAAAAAM3pTrqAB/nYx57fnHQN47a0tJCVldVJlzF2s3jeznl27Md5Hzv2eGefytnRw/Tc1l5L9QynnuHUM9ws1tNazz3oWnsPtcK4vJQxub9pH5edeq47LBrU7c5PuoSJmMXzds6zYxrPu7VzUs9w6hlOPcOph0flNbs/4/JSxuT+ZnVcBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAcwQWAAAAQHMEFgAAAEBzBBYAAABAc7qTLoBP6ffn0+l1M9+dy8JjC9lcW89gsDHpsgBg6n3WX/nRSZcwFpe+4fWTLgGAKXDn2nVpsZeVm2sju3YVWDSi35/PamcuZ89fzqVrN7J8/EjOnTmZhX6EFgAAADRhnNeupoQ0otPr5uyFK7l49XrWb23m4tXrOXvhSjo9mRIAAABtGOe1q6vhRiwt9nLp2o27jl26diNLi72svrA68ucf1y09AAAAPLxWrtnGee3qDotGrNxcy/LxI3cdWz5+JCs310b+3Hdu6Xnq/OW8+h3P5Knzl7PamUu/Pz/y5wYAAODBWrlmG+e1q8CiEZtr6zl35mROnzia7lwnp08czbkzJ7O5tj7y5zYdBQAAoF2rG7eauWYb57WrK9JGDAYbWegnTz95auy3+Ex6OgoAAAA7O7TQbeaabZzXriMLLEopH07yW1vffjTJ30zy3iT9JKtJztRar5dSviXJlyRZT/K2WuuHRlVT6waDjWSwkcXe/FjfdHdu6bl49fonj41rOgoAAADDvbi63tQ1251r11Fft45kSkgp5WVJUmt9Yut/b0ny95O8s9b6+twOLl5dSjmV5A1JXpPkTJL3jKIehpvkdBQAAACGW5ifm8lrtlHdYfG5SQ6VUp7deo53JPkdSf54KeVvJ7mU5C8neWuSZ2utm0l+rZTSLaUcq7V+bER1cR+TnI4CAADAgy1s3pq5a7ZRBRYvJvmOJN+d5LOSfCDJ8SRfl+SdW8e/MsnLk1zf9veeT/KKJJ8MLJaWFtLtztZuFfPzczl8+NBEnntj/VYWe/NJbz6HxlzCJM97Upzz7Dgo5/0wPbe1c1LPcOohyZ7HvLXXq7V69mqWPudOy2u234zLSxmT+5ufn8uhQwtJJnvNNm6jCiw+kuRXtu6c+Egp5eNJjtdafzxJSin/LMkbk/xykse3/b3Hkzy3/YFWVmZv0cfDhw/luedenHQZYzeL5+2cZ8d+nPexY48/+Jce0cP03NZeS/UMpx6S7HnMW3u9xlFPaz33oGvtPdQK4/JSxuT+pn1cduq5o9rW9KuSvDtJSimvzO0g4hdKKX9o6+evT/Kvk/xMkjeVUuZKKZ+RZK7W+vER1QQAAAAcEKO6w+J7kryvlPLTSTZzO8B4Icl7Sind3N415C/VWgellA8muZjb4clbR1QPAAAAcICMJLCotQ6SvPk+P3rdfX73W5N86yjqAAAAAA6mUU0JAQAAANgzgQUAAADQHIEFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0ByBBQAAANAcgQUAAADQHIEFAAAA0ByBBQAAANCc7qQLgNb0+/Pp9LpZWuxl5eZaNtfWMxhsTLosAACAJozrmklgAdv0+/NZ7czl7PnLuXTtRpaPH8m5Myez0I/QAgAAmHnjvGYyJQS26fS6OXvhSi5evZ71W5u5ePV6zl64kk5PtgcAADDOayaBBWyztNjLpWs37jp26dqNLC32JlQRAABAO8Z5zSSwgG1Wbq5l+fiRu44tHz+SlZtrE6oIAACgHeO8ZhJYwDaba+s5d+ZkTp84mu5cJ6dPHM25MyezubY+6dIAAAAmbpzXTCbmwzaDwUYW+snTT56ySwgAAMA9xnnNJLCAewwGG8lgI6svrE66FAAAgOaM65rJlBAAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOQILAAAAoDkCCwAAAKA5AgsAAACgOd1RPXAp5cNJfmvr248m+adJvj3Jr28d+5YkH0zy95J8bpLVJF9da/2VUdUEAAAAHAwjCSxKKS9LklrrE9uO/Y0k31Rrff+2Y1+e5GW11tOllNcmeXeSLxtFTQAAAMDBMao7LD43yaFSyrNbz/H2JJ+f5PNKKW9L8qEkfynJ65L8aJLUWn+2lPIFI6oHAAAAOEBGtYbFi0m+I8mbknxNku9P8uNJvi7J65MsbR1/eT41bSRJNkopI5umAgAAABwMowoHPpLkV2qtm0k+Ukq5nuQHaq2/niSllH+S5E/mdljx+La/N1drXd/+QEtLC+l250dUZpvm5+dy+PChSZcxdrN43s55dhyU836YntvaOalnOPWQZM9j3trr1Vo9ezVLn3On5TXbb8blpYzJ/c3quIwqsPiqJJ+T5C+UUl6Z5BVJfq6U8gdqrf8+yRcl+YUk/yHJH0/yQ1trWPyrex9oZWV1RCW26/DhQ3nuuRcnXcbYzeJ5O+fZsR/nfezY4w/+pUf0MD23tddSPcOphyR7HvPWXq9x1NNazz3oWnsPtcK4vJQxub9pH5edeu6oAovvSfK+UspPJ9lM8pbcngbyv5dSbib5N0m+K8lGkjeWUv5lks7W7wEAAAAzbiSBRa11kOTN9/nRs/c59jWjqAEAAAA4uEa16CYAAADAngksAAAAgOYILAAAAIDmCCwAAACA5ggsAAAAgOYILAAAAIDmCCwAAACA5ggsAAAAgOYILAAAAIDmCCwAAACA5ggsAAAAgOYILAAAAIDmdCddAACwO8vv/qmxP+elb3j92J8TACBxhwUAAADQIIEFAAAA0BxTQu7R78+n0+tmabGXlZtr2Vxbz2CwMemyAAAAmGGzeK0qsNim35/PamcuZ89fzqVrN7J8/EjOnTmZhX6m/o0AAABAu2bxWtWUkG06vW7OXriSi1evZ/3WZi5evZ6zF66k05PrAAAAMBmrG7dm8lpVYLHN0mIvl67duOvYpWs3srTYm1BFAAAAzLpDC92ZvFYVWGyzcnMty8eP3HVs+fiRrNxcm1BFAAAAzLoXV9dn8lpVYLHN5tp6zp05mdMnjqY718npE0dz7szJbK6tT7o0AAAAZtTC/NxMXqtO94SXhzQYbGShnzz95KmZWnkVAACAti1s3pq5a1WBxT0Gg41ksJHVF1YnXcojmcUtbwAAAEZpktdZ03Kt+jAEFlPI9qwAAAD7y3XW+FnDYgrZnhUAAGB/uc4aP4HFFLI9KwAAwP5ynTV+AospNGx71n5/PguPLeTopy9l4bGF9PvzE6oSAADg4Bh2nZXEtdYICCym0E7bs85t3spqZy5Pnb+cV7/jmTx1/nJWO3P+QwIAAHiAna6zNtfWP7m+hWut/WWyzRTaaXvWW51uzl64nItXryfJJ+dcPf3kqcQiMQAAADva6TprMNjIwmMLOXvetdZ+G1lgUUr5cJLf2vr2o7XWt2wdf0eSz6m1ntn6/luSfEmS9SRvq7V+aFQ1zZL7bXlz9OWLO8652lxbtw0qAADANvfbxnT1hdWXbC06bH2LWdqGdL+NJLAopbwsSWqtT9xz/IuTfHGSf7/1/akkb0jymiSvSvL+JMujqIlPzbm6k/olW3Oufnvd9jwAAADbPMw2pjtea22tb8HejGoNi89NcqiU8mwp5cdKKa8tpfyeJE8l+dZtv/e6JM/WWjdrrb+WpFtKOTaimmbeTnOu5juxPQ8AAMA2D7ON6bD1Ldi7UV2RvpjkO5J8d5LPSvJMkmtJ3pzk9237vZcnub7t++eTvCLJx+4cWFpaSLc7WwuVzM/P5fDhQyN57ENJvuvPfH4OLXTz4up6FubnMt+d2/H2pcXe+MZ+lOfdKuc8Ow7KeT9Mz23tnNQzGqM6h2kZn4Nmr2Pe2uvVWj17NUufc6flNdtvxuWlWhqTh71Out+1VpIc2ofTaWlcxmlUgcVHkvxKrXUzyUdKKRtJjif5wSSHk7yylPKXk3wiyePb/t7jSZ7b/kArK7M33+fw4UN57rkXR/ocN5/f+jPJwmMLO96+NM75Vvee9/3mi03bFJVxvNatmcVzTvbnvI8de/zBv/SIHqbntvZaqmc0RnUO0zI+B81ex7y112sc9bTWcw+61t5DrTAuL/WwYzLKa4a9Xidtv9baL9P+Xtmp545qSshXJXl3kpRSXpnkVpKytabF25L8WK31byf5mSRvKqXMlVI+I8lcrfXjI6qJHbR4+5JtgQAAgGFGfc3Q4nXSrBnVHRbfk+R9pZSfTrKZ5KtqrS95VWutv1BK+WCSi7kdnrx1RPUwxLDteSal0+vaFggAANjRqK8ZWrxOmjUjCSxqrYPcXq/ifj/7iSQ/se37b83dC3EyAffbBnWSbAsEAAAMM45rhtauk2bNqKaEwCO5sy3QdrYFAgAA7nDNMP0EFjTJfDEAAGAY1wzTb1RrWMAjMV8MAAAYxjXD9BNY0CzzxQAAgGFcM0w3U0IAAACA5ggsAAAAgOYILAAAAIDmCCwAAACA5ggsAAAAgOYILAAAAIDmCCwAAACA5nQnXQAP1u/Pp9PrZmmxl5Wba9lcW7+93zAAAMCEuV5hVAQWjev357PamcvZ85dz6dqNLB8/knNnTmahH00AAACYKNcrjJIpIY3r9Lo5e+FKLl69nvVbm7l49XrOXriSTk/WBAAATJbrFUZJYNG4pcVeLl27cdexS9duZGmxN6GKAAAAbnO9wigJLBq3cnMty8eP3HVs+fiRrNxcm1BFAAAAt7leYZQEFo3bXFvPuTMnc/rE0XTnOjl94mjOnTmZzbX1SZcGAADMONcrjJKJRY0bDDay0E+efvKUVXcBAICmuF5hlAQWB8BgsJEMNrL6wuqkSwEAALiL6xVGxZQQAAAAoDkCCwAAAKA5AgsAAACgOdawAGZWvz+fTq9rgSgAgAm787lsvjuXhccWfC4jicACmFH9/nxWO3M5e/5yLl27keXjR3LuzMks9OP/HAEAxsjnMnZiSggwkzq9bs5euJKLV69n/dZmLl69nrMXrqTTk+MCAIyTz2XsRGABzKSlxV4uXbtx17FL125kabE3oYoAAGaTz2XsZOoDi35/PguPLeTopy9l4bGF9Pvzky4JaMDKzbUsHz9y17Hl40eycnNtQhUBAMymR/lc5npvuk11YHFnLtRT5y/n1e94Jk+dv5zVzpw3MZDNtfWcO3Myp08cTXeuk9MnjubcmZPZXFufdGkAADNlr5/LXO9Nv6meFNTpdXP2/OVcvHo9ST45F+rpJ08lFm+BmTYYbGShnzz95Cm7hAAATNBeP5e53pt+IwssSikfTvJbW99+NMn3JvmOJJtJ/q9a61/b+r1vSfIlSdaTvK3W+qH9qmHYXKjVF1b362l4RLYwYlIGg41ksDHSfuD9DQAcROPe/v3O57LF3vyuP5s96HrPFvYH30gCi1LKy5Kk1vrEtmO/kOS/qbV+tJTy46WUf5qkk+QNSV6T5FVJ3p9keb/quDMX6k7ilpij3hpbGDHNvL8BgIPooHyGGXa9d1DOgeFGtYbF5yY5VEp5tpTyY6WU1yZ5zVZYsZTkFUmuJ3ldkmdrrZu11l9L0i2lHNuvIsxRb58tjJhm3t8AwEF0UD7DDLveOyjnwHCjerVezO3pH9+d5LOSPJOkbAUXF5L8myQfS/Ly3A4u7ng+t8OMj905sLS0kG5374umHEryXX/m83NooZsXV9ezMH87ozl0aM8POXLz83M5fLjhAvfRfHdux9u4FnvTv1jOLL3Wd8zSOR/E9/fD9NzWXkv1jMaozmFaxueg2euYt/Z6tVbPXj3q59z/n737j7Izr+/D/p4f986OdgSKZLlAbKojCt+4jY28ZmxUE8AONja0dWzjWpCNi9e465QkIoc0NcE+rG1Skh725KipDWtDSlM5FjmHtD1NsmbjUn7LZoqQa9f2dw1CtmtiAlK17OyKuTOj6R8zgpGQ5od2nnufe+/rdc4e3Xnmzp3P9/n1fea9z/f5DpNR2WZ7ra3rZZDXMLtdJ7f7e28Yr8O20tZ9pWlNBRaPJvl0rXUtyaOllEtJnllr/c0kR0opb03y01kPK/Zv+rn9Sa5s/qDFxb0ZW3718Y1/9+TTmnXgwL5cufLkoMvoi5m7Z257G9c4PGdknLb1dePU5r3evw8f3r/9m56i3Zxz27Yt1dOMptowKutn2NzpOm/b9upHPW075w67tu1DbdHW9TLIa/Q7XSc3/703an9ntHVf2Su3O+c2NSTkviQPJkkp5VlZv2vin5dS/tzG9x9Pci3Jx5K8vJQyWUp5dpLJWusXG6qJFjJsh1Fm/wYAhtEoXMOMQhto7g6Ldyd5Tynlo1mfFeTHkxxO8nApZSnJv03yulrrYinlI0nOZj08eX1D9dBSppZklNm/AYBhNArXMKPQBnYQWJRS3lRrfdtuPrTW2kvymlt863+7xXsfSPLAbj6f0XInUxjBsLB/AwDDqB/TvzdtFNow7nYyJOR7Gq+CodPtTmXm7pkc+rq5zNw9k253+B5cAwAADBd/h4yXnQwJOVRK+d5bfaPW+sge18MQMKcxALAT8w9+uO+/c+GNL+777wT6w98h42cnd1h8fZITSV59038nGqyLFjOnMQAA0G/+Dhk/O9myf1Brva/xShgac7Od285pbHwYAADQBH+HjJ+d3GHh3hpusHh1OfNHDt6w7PqcxgAAAE3wd8j42TawqLW+7OZlpZS/WEp5ZzMl0XbmNAYAAPrN3yHjZ8eDfUopU0l+KMnfSPLvJXlXU0XRbuY0BgAA+s3fIeNn28CilPKMJPcn+WtJziaZqbX+haYLo93MaQwAAPSbv0PGy06eYfHpJDNJvrXW+teS/H/NlgQAAACMu50EFj+R5AVJPlBK+etJus2WBAAAAIy7nTx087211u9N8iNJnpXkaCnlvaWU/6Tx6gAAAICxtJM7LJIktdaLtdafTfKcJP9zkp9srCoAAABgrO0osCil/MDGv09L8g+TvDDJaxqsCwAAABhj2wYWpZR/kOTHNqY1/R+SzCW5lOQdDdcGAAAAjKmd3GHxbbXWH04ykeSVSd5Ya/1HSY42WhkAAAAwtnYSWKxs/PvtSX631vrkxtdmCwEAAAAaMb2D96yWUr43yWuTvC9JSikvS3KlwboAAACAMbaTOyxOJvmJJH+S5B2llJcneTDJ32yyMAAAAGB8bXuHRa31M0l+dNOi92/8lyQppdxfa32ogdoAAACAMbWjaU238aPbvwUAAABg5/YisJjYg88AAAAA+Iq9CCzW9uAzAAAAAL5iLwILAAAAgD1lSAgAAADQOtvOElJKeTDJryf5UK21d4u3/N09rwoAAAAYa9sGFkl+J8lfTXKqlPLZrIcXv15r/cMkqbUuNFgfAAAAMIa2DSxqre9J8p4kKaUcSfLSJP+klPKsWutzGqwNAAAAGFM7ucMipZRnJ3nFxn/fkOQTSd7eYF0AAADAGNvJMyx+O8m/S/Jwkp+utf5e41UBAAAAY20nd1j8ZpIXJLknyedLKZ+vtV7a7odKKZ9K8tjGl59NcjrJW5MsZz0A+bFa65OllLckeWWSlSRvqLV+YvfNgPHU7U5lojOdudlOFq8uZ215Jb3e6qDLAgAYO67LYO/t5BkW9ydJKeUvJvn+JGdKKd0kv1Fr/YVb/Uwp5a6Nn33ppmU1yYtrrZ8vpbwtyetKKR9N8pIk35HkG5O8L8n8U2oRjIludypLE5M5efpcFi5ezvyRgzl14lhmutE5AgD0kesyaMbkLt77/yb5/STnkkxkPWi4necn2VdKeaSU8oFSyguTvLTW+vmN708n+XKSFyV5pNa6Vmv94yTTpZTDu24FjKGJznROnjmfsxcuZeXaWs5euJSTZ85norOjR9MAALBHXJdBM3byDItfzHqwcC3J/5Hk3yR5oNZ6dYsfezLrD+V8V5LnZv35F2Xj834wyXcl+dkkfyfJ5uEljyd5epIvXF8wNzeT6empnbdoBExNTebAgX2DLqPvxrHdT6XNU9OTWbh4+YZlCxcvZ262k9lOe4+ZcdzOyfC0ezfn3La1ST3NaKoNo7J+hs0d9zlDtL2Gpc5kvK5zh2kfuhN3el026uvlTlgntzau62Wnz7D4hVrrn21eWEqZ3SK0eDTJp2uta0keLaVcSvLMUsqrkrwqyffVWr9cSvlSkv2bfm5/kiubP2hxcWmHTRkdBw7sy5UrTw66jL4bx3Y/lTbP3D2T+SMHc/bCVzO/+SMHs3h1OUtPtPe4GcftnOxNuw8f3r/9m56i3Zxz27Yt1dOMptowKutn2NzpOh+m7bVXdbbtnDvshmkfuhN3el026uvlTlgntzbq6+V259ydDAn5SJK/V0r5uVLKviQppbwiye9s8TP3JXlw473PSvK0jWV/KcnLaq1f3Hjfx5K8vJQyuTF16uSm7wFbWFteyakTx3L86KFMT07k+NFDOXXiWNaWVwZdGgDAWHFdBs3YyR0W/yzJe5L8+0l+vpTSS/JDSV67xc+8O8l7Nh6quZbk/qwPJTmX5OFSSpK8t9b6jlLKR5KczXp48vo7awaMn15vNTPd5KF77/E0agCAAXJdBs3YSWBxrdb6y0lSSrmY5ENJjtVav3y7H6i19pK85qbF3du894EkD+ygDuAmvd5q0ltt9RAQAIBx4LoM9t5OAovlTa8vJXntxrMpAAAAABqxk2dYbA4nHhNWAAAAAE3byR0WLyqlfC7JRJKDm16v1Vqf1Wh1AAAAwFjaNrCotd7y2RMAAAAATdk2sCilTCX5gSR/lOTRrE9X2k3yllrrHzVbHgAAADCOdjIk5JeSzCXZn+Trk7w/yZ8k+R+TfHdzpQEAAADjaicP3fzmWutfTfKDSf5crfUttdZ3JbnWbGkAAADAuNpJYPHlJKm1rib5013+LAAAAMCu7WRIyKFSyvdmfWaQza8PNloZAAAAMLZ2ElicS/LqW7z+/UYqAgAAAMbeTgKLfbXWH02SUsoba60Pbrz+QKOVAQAAAGNrJ8+hOLzp9SubKgQAAADgup0EFhO3eQ0AAADQiJ0EFmu3eQ0AAADQiJ08w+I/KqX8s6zfXbH59X/YaGUAAADA2NpJYPGfb3r9ztu8BgAAANgz2wYWtdYP9aMQAAAAgOt28gwLAAAAgL7ayZAQWqrbncpEZzpzs50sXl3O2vJKer3VQZcFjdvtvu9YAQB2qonrhn5fi7j2YVQILIZUtzuVpYnJnDx9LgsXL2f+yMGcOnEsM904GTHSdrvvO1YAgJ1q4rphq89sgmsfRokhIUNqojOdk2fO5+yFS1m5tpazFy7l5JnzmejIoBhtu933HSsAwE41cd3Q72sR1z6MEoHFkJqb7WTh4uUbli1cvJy52c6AKoL+2O2+71gBAHaqieuGfl+LuPZhlAgshtTi1eXMHzl4w7L5IwezeHV5QBVBf+x233esAAA71cR1Q7+vRVz7MEoEFkNqbXklp04cy/GjhzI9OZHjRw/l1IljWVteGXRp0Kjd7vuOFQBgp5q4buj3tYhrH0aJgUxDqtdbzUw3eejeezz9l7Gy233fsQIA7FQT1w1bfea+fXtY/A5+HwwbgcUQ6/VWk95qlp5YGnQp0Fe73fcdKwDATjVx3dDvaxHXPowKQ0IAAACA1hFYAAAAAK0jsAAAAABap7FnWJRSPpXksY0vP1tr/fFSylSS9yZ5V6311zfe92Ol+LsAACAASURBVJYkr0yykuQNtdZPNFUTAAAAMBwaCSxKKXclSa31pZuWPSfJ/5TkG5O8a2PZPUlekuQ7Npa/L8l8EzUBAAAAw6OpOyyen2RfKeWRjd/x95JcTfKTSf6bTe97UZJHaq1rSf64lDJdSjlca/1CQ3UBAAAAQ6CpwOLJJG/P+p0Uz03ycJJSa10ppWx+39OSXNr09eNJnp7kK4HF3NxMpqenGiqznaamJnPgQAOTMrfcOLZbm8fD0uq1TE1PZnb/XZmZavejg3Zzzm3btlRPM5pqw6isn2Fzp+t8mLbXsNSZjNd17jDtQ9tZWr2WfTPTeXJp5Sn366O0XvaKdXJr47pemgosHk3y6Y07Jx4tpVxK8swkf3LT+76UZP+mr/cnubL5DYuL4zd38IED+3LlypODLqPvxrHd2jzaut2pLE1M5uSZ81m4eDnzRw7m1IljmVm7tj4/+i4dPrx/+zc9Rbs557ZtW6qnGU21YVTWz7C503U+TNtrr+ps2zl32A3TPnQ7e92vJ6OxXvaadXJro75ebnfObep/9d2X5MEkKaU8K+t3UvzbW7zvY0leXkqZLKU8O8lkrfWLDdUE0FcTnemcPHM+Zy9cysq1tZy9cCknz5zPRKex5x0DAA3Rr0P/NRVYvDvJgVLKR7M+K8h9tdaVm99Ua/1kko8kOZv1B26+vqF6APpubraThYuXb1i2cPFy5mY7A6oIALhT+nXov0biwFprL8lrbvO919709QNJHmiiDoBBWry6nPkjB3P2wlcf1TN/5GAWry4PsCoA4E7o16H/2v30N4Ahtra8klMnjuX40UOZnpzI8aOHcurEsawtf80NZwBAy+nXof8MuAJoSK+3mplu8tC992RutpPFq8tZW1654wdzAQCDo1+H/hNYADSo11tNequZ7Uxl6YnxeRo8AIyi6/26Ph36w5AQAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtM70oAsAGGXd7lQmOtOZmp7MzN0zWVteSa+3OuiyAIBNrvfXc7OdLF5d1l9DSwgsABrS7U5laWIyJ0+fy8LFy5k/cjCnThzLTDcuggCgJfTX0F6GhAA0ZKIznZNnzufshUtZubaWsxcu5eSZ85noyIoBoC3019BeAguAhszNdrJw8fINyxYuXs7cbGdAFQEAN9NfQ3sJLAAasnh1OfNHDt6wbP7IwSxeXR5QRQDAzfTX0F4CC4CGrC2v5NSJYzl+9FCmJydy/OihnDpxLGvLK4MuDQDYoL+G9jIwC6Ahvd5qZrrJQ/fe46njANBS+mtoL4EFQIN6vdWkt5rZzlSWnlgadDkAwC1c76/11dAuhoQAAAAArSOwAAAAAFpHYAEAAAC0TmPPsCilfCrJYxtffjbJQ0lOJVlJ8kit9edKKZNJfinJ85MsJXldrfXTTdUEAAAADIdGAotSyl1JUmt96aZl55P8cJILSf5VKeWeJEeS3FVrPV5KeWGSB5P8QBM1AQAAAMOjqTssnp9kXynlkY3f8UCSmVrrZ5KklPL+JH85yTOT/HqS1Fp/s5TygobqAQAAAIZIU4HFk0nenuRdSZ6b5OEkVzZ9//EkR5M8LV8dNpIkq6WU6VrryvUFc3MzmZ6eaqjMdpqamsyBA/sGXUbfjWO7tXl8DEu7d3PObVub1NOMptowKutn2NzpOh+m7TUsdSbjdZ07TPtQP1kvX8s6ubVxXS9NBRaPJvl0rXUtyaOllMeSHNz0/f1ZDzD2bby+bnJzWJEki4vjNxfygQP7cuXKk4Muo+/Gsd3aPD72ot2HD+/f/k1P0W7OuW3bluppRlNtGJX1M2zudJ0P0/baqzrbds4ddsO0D/WT9fK1rJNbG/X1crtzblOzhNyX9edRpJTyrKwHE0+UUp5TSplI8vIkH0nysSSv2HjfC5P8TkP1AAAAAEOkqTss3p3kPaWUjyZZy3qAcS3JryaZyvosIb9VSllI8j2llI8nmUjy4w3VAwAAAAyRRgKLWmsvyWtu8a0X3vS+a0l+qokaAAAAgOHV1JAQAAAAgDsmsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0zPegCABg98w9+uO+/8w9/4fv6+vsG0cZBGJd2AgDt4w4LAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1plu6oNLKV+f5JNJvifJviTvTLKU5HySk7XWa6WUtyR5ZZKVJG+otX6iqXoAAACA4dHIHRallE6Sh5Jc3Vj0y1kPJP5SkseSvKaUck+SlyT5jiQnkvxiE7UAAAAAw6epISFvz/odFZ/b+Pobaq0f33j9sSQv2vjvkVrrWq31j5NMl1ION1QPAAAAMET2fEhIKeW1Sb5Qa31/KeVNG4svlFJeUmv9UJL/NMndSZ6W5NKmH308ydOTfGHz583NzWR6emqvy2y1qanJHDiwb9Bl9N04tlubx8ewtHs359y2talt9UAb3ekxMkzH17DUmYzXde4w7UP9ZL18Levk1sZ1vTTxDIv7kqyVUl6W5FiSf5rkv07yplLK302ykPVnWXwpyf5NP7c/yZWbP2xxcamBEtvtwIF9uXLlyUGX0Xfj2G5tHh970e7Dh/dv/6anaDfn3LZty9XVa62qB9roTo+Rth3vW9mrOtt2zh12w7QP9ZP18rWsk1sb9fVyu3PungcWtdYXX39dSvlgkp9K8ook99VaP1dK+cdJHk7y+ST/XSnl7Um+IclkrfWLe10PAAAAMHwamyXkJn+Y5F+XUp5M8n/WWv91kpRSPpLkbNafpfH6PtUCAAAAtFyjgUWt9aUbL/8gyf9+i+8/kOSBJmsAAAAAhk9Ts4QAAAAA3DGBBQAAANA6AgsAAACgdQQWAAAAQOsILAAAAIDWEVgAAAAArSOwAAAAAFpHYAEAAAC0jsACAAAAaB2BBQAAANA6AgsAAACgdQQWAAAAQOsILAAAAIDWEVgAAAAArSOwAAAAAFpHYAEAAAC0jsACAAAAaB2BBQAAANA6AgsAAACgdQQWAAAAQOsILAAAAIDWEVgAAAAArTM96AIARlm3O5WJznSmpiczc/dM1pZX0uutDrosAIbc9f5lbraTxavL+hdgJAksABrS7U5laWIyJ0+fy8LFy5k/cjCnThzLTDcuKgG4Y/oXYFwYEgLQkInOdE6eOZ+zFy5l5dpazl64lJNnzmeiIysG4M7pX4BxIbAAaMjcbCcLFy/fsGzh4uXMzXYGVBEAo0D/AowLgQVAQxavLmf+yMEbls0fOZjFq8sDqgiAUaB/AcaFwAKgIWvLKzl14liOHz2U6cmJHD96KKdOHMva8sqgSwNgiOlfgHFhoBtAQ3q91cx0k4fuvcdT3AHYM/oXYFw0FliUUr4+ySeTfE+Su5K8M8lKkkeTvK7Weq2U8pNJ7t9Y/tZa679sqh6AQej1VpPeamY7U1l6YmnQ5QAwIq73L/oWYJQ1MiSklNJJ8lCSqxuL3pLk52utL0oyk+SVpZRnJPlbSb4zycuTvK2UMtNEPQAAAMBwaeoZFm/P+h0Vn9v4+lNJDpZSJpLsT7Kc5NuTfKzWulRrfSzJp5N8S0P1AAAAAENkz4eElFJem+QLtdb3l1LetLH4D5P8YpKfSfJYkg8medXG6+seT/L0mz9vbm4m09NTe11mq01NTebAgX2DLqPvxrHd2jw+hqXduznntq1NbasH2uhOj5FhOr6Gpc5kvK5zh2kf6ifr5WtZJ7c2ruuliWdY3JdkrZTysiTHkvzTjX+/tdb6/5RSXp/kwSTvz/rdFtftT3Ll5g9bXBy/cXkHDuzLlStPDrqMvhvHdmvz+NiLdh8+vH/7Nz1Fuznntm1brq5ea1U90EZ3eoy07Xjfyl7V2bZz7rAbpn2on6yXr2Wd3Nqor5fbnXP3PLCotb74+utSygeT/FSS/zXJlzYWfy7rz634RJK/X0q5K+vPtfimJL+71/UAAAAAw6df05q+LsmZUspKkl6Sn6y1/lkp5b9P8pGsP0vjzbXWL/epHgAAAKDFGg0saq0v3fTld97i+7+S5FearAEAAAAYPk3NEgIAAABwxwQWAAAAQOsILAAAAIDWEVgAAAAArSOwAAAAAFpHYAEAAAC0zsTa2tqgawAAAAC4gTssAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtMz3oArbzhS88vjboGvptbm4mi4tLgy6j78ax3do8Pvai3YcP75/Yo3Juazfn3LZtS/VsTT1bU8/WxrGetp1zh13b9qG2sF6+lnVya6O+Xm53znWHRQtNT08NuoSBGMd2a/P4GMV2t61N6tmaeramnq2ph6fKNrs16+VrWSe3Nq7rRWABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrTA+6AL6q253KRGc6U9OTmbl7JmvLK+n1Vgdd1ti5vh3mZjtZvLpsOwDAU9SPvlX/DTB6BBYt0e1OZWliMidPn8vCxcuZP3Iwp04cy0w3Ots+sh0AYG/1o2/Vf8PwmH/ww33/nQtvfHHffyd7w5CQlpjoTOfkmfM5e+FSVq6t5eyFSzl55nwmOjKlfrIdAGBv9aNv1X8DjCaBRUvMzXaycPHyDcsWLl7O3GxnQBWNJ9sBAPZWP/pW/TfAaBJYtMTi1eXMHzl4w7L5IwezeHV5QBWNJ9sBAPZWP/pW/TfAaBJYtMTa8kpOnTiW40cPZXpyIsePHsqpE8eytrwy6NLGiu0AAHurH32r/htgNBnY1xK93mpmuslD997j6dYDZDsAwN7qR9+q/wYYTQKLFun1VpPeamY7U1l6YmnQ5Yyt69vBNgCAvdGPvlX/DTB6DAkBAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DrTgy6gbbrdqUx0pjM328ni1eWsLa+k11sddFmNG9d2A8AoGNd+fFzbDTAuBBabdLtTWZqYzMnT57Jw8XLmjxzMqRPHMtPNSHd+49puABgF49qPj2u7AcaJISGbTHSmc/LM+Zy9cCkr19Zy9sKlnDxzPhOd0c51xrXdADAKxrUfH9d2A4yTxs7opZRPJXls48vP1lp/fGP5m5N8c631xMbXb0nyyiQrSd5Qa/1EUzVtZ262k4WLl29YtnDxcuZmO1l6YmlAVTVvXNsNAKNgXPvxcW03wDhp5A6LUspdSVJrfenGf9fDiu9P8v2b3ndPkpck+Y4kJ5L8YhP17NTi1eXMHzl4w7L5IwezeHV5QBX1x7i2GwBGwbj24+PaboBx0tSQkOcn2VdKeaSU8oFSygtLKf9BkvuTPLDpfS9K8kitda3W+sdJpksphxuqaVtryys5deJYjh89lOnJiRw/eiinThzL2vLKoErqi3FtNwCMgnHtx8e13QDjpKkhIU8meXuSdyV5bpKHk1xM8pok37TpfU9LcmnT148neXqSL1xfMDc3k+npqYbK/Fr7kvzKj31b9s1M58mllcxMrWc6+/b1rYRMTU3mwIE+/sKMb7sHTZvHx7C0ezfn3La1ST1bU8/Whr2epvvxNq6ffftmWnH98lT0+zp3kNq2D7WF9dIfo7COx3VfaSqweDTJp2uta0keLaWsJjmS5L1JDiR5Vinlp5N8Kcn+TT+3P8mVzR+0uDiYMYhXH9/4dwC/+8CBfbly5ckB/ObxbfegaPP42It2Hz68f/s3PUW7Oee2bVuqZ2vq2dqo1NNUP9729dNEu9t2zh12bduH2sJ66Y9RWMejvq/c7pzb1JCQ+5I8mCSllGcluZak1FpfmuQNST5Qa/0HST6W5OWllMlSyrOTTNZav9hQTQAAAMCQaCqweHeSA6WUj2b9ror7aq1fM6Cw1vrJJB9JcjbJ+5K8vqF6AAAAgCHSyJCQWmsv68+ruNX3Ppjkg5u+fiA3PogTAAAAGHNN3WEBAAAAcMcEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtI7AAgAAAGgdgQUAAADQOgILAAAAoHUEFgAAAEDrCCwAAACA1hFYAAAAAK0jsAAAAABaR2ABAAAAtM70oAugv7rdqUx0pjM328ni1eWsLa+k11sddFkAwC3otwEYZwKLMdLtTmVpYjInT5/LwsXLmT9yMKdOHMtMNy5+AKBl9NsAjDtDQsbIRGc6J8+cz9kLl7JybS1nL1zKyTPnM9GRWwFA2+i3ARh3erwxMjfbycLFyzcsW7h4OXOznSw9sTSgqgCAW9Fvw2DNP/jhvv/OhTe+uO+/E9rMHRZjZPHqcuaPHLxh2fyRg1m8ujygigCA29FvAzDuBBZjZG15JadOHMvxo4cyPTmR40cP5dSJY1lbXhl0aQDATfTbAIw7Q0LGSK+3mplu8tC993jaOAC0nH4bgHEnsBhRt5sGrddbTXqrxr4CwBDY3G9f79sPPW1WeAHAWBBYjCDToAHAaNG3AzCOPMNiBJkGDQBGi74dgHEksBhBW02Ddjvd7lRm7p7Joa+by8zdM+l2p5ouEwC4yfX+eGp68ob++E76dgAYdgKLEbTbadCu32Z6/+lzed6bH879p89laWJSaAEAfbRVf2yKUwDGkcBiBO12GjS3mQLA4G3VH5viFIBx5C/SEbTbadC2us3UbCIA0B9b9ceXnlgyxSkAY8cdFiOqtzEF2qUvLmbpiaUtL2jcZgoAg7ddf7ybvh0ARoHAAreZAkAL6I8B4EaGhLDrISQAwN7THwPAjQQWJFm/SMrGraYAwGBc749nO1P6ZADGniEhAAAAQOsILAAAAIDWEVgAAAAArSOwAAAAAFpHYAEAAAC0jsACAAAAaB2BBQAAANA6AgsAAACgdQQWAAAAQOsILAAAAIDWmR50AdDtTmWiM52p6cnM3D2TteWV9Hqrgy4LgDGgDwKA9hJYMFDd7lSWJiZz8vS5LFy8nPkjB3PqxLHMdOOCEYBG6YMAoN0MCWGgJjrTOXnmfM5euJSVa2s5e+FSTp45n4mOLA2AZumDAKDdBBYM1NxsJwsXL9+wbOHi5czNdgZUEQDjQh8EAO0msGCgFq8uZ/7IwRuWzR85mMWrywOqCIBxoQ8CgHYTWDBQa8srOXXiWI4fPZTpyYkcP3oop04cy9ryyqBLA2DE6YMAoN0M0mSger3VzHSTh+69J3OznSxeXfaEdgD6Qh8EAO028oHF9enKXIi0V6+3mvRWM9uZytITS19ZbtsB0LTNfdDa8komOtM59LTZvvU7+joAuL2RDixMVza8bDsA+q3f/c5WfR0AMOLPsDBd2fCy7QDop6XVa33vd/R1ALC1kQ4sTFc2vGw7APpp38x03/sdfR0AbG2kAwvTlTWn253KzN0zOfR1c5m5eybd7tSefr5tB8Be2Umf9eTSSt/7HX0dAGxtpAML05U14/qY2/tPn8vz3vxw7j99LksTk3saWth2AOyFnfZZM1OTfe939HUAsLWRHiRpurJmTHSmc/L0uZy9cClJvjLm9qF770n2aN3adgDshd30WTNr1/ra72zV1+3b19ivBYChMdKBRfLV6co2T5fJU7PVmNu9XM+2HQBP1W76rEH0O/o6ALi9kR4SQjOMuQVgWOizAGB4CSzYNWNuARgW+iwAGF4jPySEvef5EgAMC30WAAwvgQV3xJhbAIaFPgsAhpMhIQAAAEDrCCwAAACA1mlsSEgp5VNJHtv48rNJTid5a5LlJP8uyY/VWp8spbwlySuTrCR5Q631E03VBLBZtzuVic60ce3ALTlHAMBgNRJYlFLuSpJa60s3LatJXlxr/Xwp5W1JXldK+WiSlyT5jiTfmOR9SeabqAlgs253KksTkzl5+lwWLl7O/JGDOXXiWGa68QcJ4BwBAC3Q1JCQ5yfZV0p5pJTygVLKC5O8tNb6+Y3vTyf5cpIXJXmk1rpWa/3jJNOllMMN1QTwFROd6Zw8cz5nL1zKyrW1nL1wKSfPnM9Ex7OIAecIAGiDpnrdJ5O8Pcm7kjw3ycNJSpKUUn4wyXcl+dkkfyfJpU0/93iSpyf5wvUFc3MzmZ6eaqjMdpqamsyBA/sGXUbfjWO7tXmAdUxPZuHi5RuWLVy8nLnZTmY7e3/OaUu7t7Obc27b2qSeralnazfX0+9zxHb1DJp6mjFO17mjss2aZh01YxTW67geQ00FFo8m+XStdS3Jo6WUS0meWUp5VZJXJfm+WuuXSylfSrJ/08/tT3Jl8wctLo7fFGQHDuzLlStPDrqMvhvHdmvz4MzcPZP5Iwdz9sJXM9P5IwezeHW5kakP96Ldhw/v3/5NT9Fuzrlt2ZbXqWdr6tnazfX0+xyxXT2DNo71tO2cO+zatg+1lXXUjFFYr6N+DN3unNvUkJD7kjyYJKWUZyV52sayv5TkZbXWL26872NJXl5KmSylPDvJ5KbvATRmbXklp04cy/GjhzI9OZHjRw/l1IljWVteGXRpQAs4RwDA4DV1h8W7k7xn46Gaa0nuT/JvkpxL8nApJUneW2t9RynlI0nOZj08eX1D9QDcoNdbzUw3eejee8wAAHwN5wgAGLxGAotaay/Ja25a3L3Nex9I8kATdQBspddbTXqrfbm9Gxg+zhEAMFhNDQkBAAAAuGMCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DrTgy4AAAAAmjL/4If7/jsX3vjivv/OUbTtHRallGf2oxBur9udyszdMzn0dXOZuXsm3e7UoEsCADbRVwPA3tvJkJBfbbwKbqvbncrSxGTuP30uz3vzw7n/9LksTUy6EAKAltBXA0AzPMOi5SY60zl55nzOXriUlWtrOXvhUk6eOZ+JjtE8ANAG+moAaMZOetJvK6V8/KZlE0nWaq3/cQM1scncbCcLFy/fsGzh4uXMzXay9MTSgKoCAK7TVwNAM3YSWPxeklc3XQi3tnh1OfNHDubshUtfWTZ/5GAWry4PsCoA4Dp9NQA0YyeBxZdrrX/UeCXc0trySk6dOJaTZ85n4eLlzB85mFMnjmVteWXQpQEA0VcDQFN2Eli8+1YLSyl/vtb6p3tcDzfp9VYz000euveezM12snh1OWvLK+n1VgddGgAQfTUANGXbwKLWenrz16WU70ryN5J8Z5JnNFQXm/R6q0lv1ThYAGgpfTUA7L0dPb66lHJ3ktcm+etZDyn+ZpLXNFcWAAAAMM62nda0lPKPk3wiyTOT/JUkC7XWX6u1+l8IAAAAQCN2cofFi5J8MslvJbmQZK3RigBGSLc7lYnOdKamJzNz94xx7dAyjlEAaK9t77CotX5rkncm+aEkNcnzSil/oenCAIZdtzuVpYnJ3H/6XJ735odz/+lzWZqYTLc7NejSgDhGAaDttg0skqTW+vFa648nuSfJg0lOl1L+r0YrAxhyE53pnDxzPmcvXMrKtbWcvXApJ8+cz0RnR48PAhrmGAWAdttRYHFdrfXxJL+W5LuTvK6RigBGxNxsJwsXL9+wbOHi5czNdgZUEbCZYxQA2m0nD928p5TyqVJKp5RyfVjIQpJvbLw6gCG2eHU580cO3rBs/sjBLF5dHlBFwGaOUQBot53cYfH3k/wXtdblJG9N8v1J5pP8dJOFAQy7teWVnDpxLMePHsr05ESOHz2UUyeOZW15ZdClAXGMAkDb7WSQ5mSt9f8upTwryd211nNJUkq51mxpAMOt11vNTDd56N57MjfbyeLVZTMQQIs4RgGg3XYUWGz8+31JfiNJSikzSfY3VRTAqOj1VpPeamY7U1l6YmnQ5QA3cYwCQHvtJLD4jVLKx7L+zIr/rJTynCTvSPLeRisDAAAAxta2z7Cotf7DrM8I8q211vMbi99Ra31b8pW7LQAAAAD2zI4mGq+1/v6m159J8plN334469OcAgAAAOyJncwSsp2JPfgMAAAAgK/Yi8BibQ8+AwAAAOAr9iKwAAAAANhThoQAAAAArbMXgcXv7cFnAAAAAHzFjmYJSZJSyiuT/FdJZq8vq7V+d6319U0UBgAAAIyvHQcWSX4hyd9O8mcN1QIAAACQZHeBxeVa64caq4Rd63anMtGZztxsJ4tXl7O2vJJeb3XQZQEwpPQrAECbbBtYlFL+y42XvVLKLyf5ZDamMq21/nKDtbGFbncqSxOTOXn6XBYuXs78kYM5deJYZrpxcQnArulXAIC22clDN5+58d9vJfnTJM/Y+PoZDdbFNiY60zl55nzOXriUlWtrOXvhUk6eOZ+Jzm5umgGAdfoVAKBttr0KMMGTKgAAHh9JREFUqbX+XJKUUn6m1vrW68tLKW9rsjC2NjfbycLFyzcsW7h4OXOznSw9sTSgqgAYVvoVAKBtdjIk5CeSvC7JN5VSXrGxeDJJN8mbGqyNLSxeXc78kYM5e+HSV5bNHzmYxavLA6wKgGGlXwEA2mYnQ0JOJ3l1kn++8e+rk/xIkuMN1sU21pZXcurEsRw/eijTkxM5fvRQTp04lrXllUGXBsAQ0q8AAG2zkyEhS0kullJen+QFSTpJJpK8KMmvNVset9PrrWammzx07z2e5g7AU6ZfAQDaZjdP0npf1oeB/PkkU0k+F4HFQPV6q0lv1dhiAPaEfgUAaJOdDAm57um11u/L+mwh35bkrmZKAgAAAMbdbgKL64NY7661Xk0y00A9AAAAALsKLP5FKeVnk/x2KeVskscaqgkAAAAYczuZ1vSfbPpyKsm1rD+/wjxnAAAAQCN28tDNFyTZl/XpTT+e9RlCAAAAABqz7ZCQWuu3JPkrWX/I5k8nOZ7kM7XW9zdcGwAAADCmdjStaa31d7MeVqSU8uIkbyulfGOt9YVNFgcAAACMpx0FFklSSnlakh9M8uokd2d9iAgAAADAntvJQzd/JOshxbOT/IskP1VrvdhwXQAAAMAY28kdFu9N8gdJfjvJNyf5b0spSZJa62uaKw0AAAAYVzsJLL6r8SoAAAAANtk2sKi1fqgfhQAAAABct+20pgAAAAD9JrAAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0Do7mdb0jpRSPpXksY0vP5vkoSSnkqwkeaTW+nOllMkkv5Tk+UmWkryu1vrppmoCAAAAhkMjgUUp5a4kqbW+dNOy80l+OMmFJP+qlHJPkiNJ7qq1Hi+lvDDJg0l+oImaAAAAgOHR1B0Wz0+yr5TyyMbveCDJTK31M0lSSnl/kr+c5JlJfj1Jaq2/WUp5QUP1AAAAAEOkqcDiySRvT/KuJM9N8nCSK5u+/3iSo0melq8OG0mS1VLKdK115fqCubmZTE9PNVRmO01NTebAgX2DLqPvxrHd2jw+hqXduznntq1N6tmaeramnq2ppxnjdJ07KtusadbR6NjrbTmux1BTgcWjST5da11L8mgp5bEkBzd9f3/WA4x9G6+vm9wcViTJ4uJSQyW214ED+3LlypODLqPvxrHd2twf3e5UJjrTmZvtZPHqctaWV9Lrrfa1hr1o9+HD+7d/01O0m3Nu2/Zf9WxtJ/X081gZxvXTT+rZWj/qads5d9i1bR9qK+todOz1thz1Y+h259ymZgm5L+vPo0gp5VlZDyaeKKU8p5QykeTlST6S5GNJXrHxvhcm+Z2G6gHGVLc7laWJydx/+lye9+aHc//pc1mamEy3Ox7/Rwt2yrECALRNU4HFu5McKKV8NMl7sx5gvC7Jryb5RJJP1Vp/K8n/kuTLpZSPJ/lHSf52Q/UAY2qiM52TZ87n7IVLWbm2lrMXLuXkmfOZ6DQ2SRIMJccKANA2jVyF1Fp7SV5zi2+98Kb3XUvyU03UAJAkc7OdLFy8fMOyhYuXMzfbydIT43MrLmzHsQIAtE1Td1gAtMLi1eXMHzl4w7L5IwezeHV5QBVBOzlWAIC2cZ8nMNLWlldy6sSxnDxzPgsXL2f+yMGcOnEsa8sr2/8wjBHHCsB4mn/ww4MuYSSNy3pdeOOLG/18gQUw0nq91cx0k4fuvWegs4RA2zlWAIC2EVjAEGvDdJ3DoNdbTXqrxuHDNvpxrFw/b01NT2bm7hnnLQDgtgQWMKSuT0F48vS5G27fnunGxT/QSs5bAMBueOgmDClTEALDxnkLANgNgQUMqa2mIARoI+ctAGA3BBYwpExBCAwb5y0AYDcEFjCkrk9BePzooUxPTuT40UOmIARazXkLANgNg0ZhSJmCEBg2zlsAwG4ILGCIma6z/UzhSL+1fbrj6+et2c6UcxcAsCWBBUBDTOFIv221zwEADBvPsABoiCkc6Tf7HAAwSgQWAA0xhSP9Zp8DAEaJwAKgIaZwpN/scwDAKBFYADTEFI70m30OABglBrUCNMQUjvTbVvvcvn2Drg4AYHcEFsDQafu0jZuZwpF+eyrTHQ/TsQUAjD6BBTBUTBUKzXBsAQBt4xkWwFAxbSM0w7EFALSNwAIYKsM2bWO3O5WZu2cyNT2Zmbtn0u1ODbokWuL6vnHo6+ZasW8M27EFAIw+gQUwVIZp2sbrt9jff/pcnvfmh3P/6XNZmpgc+B+mDF4b941hOrYAgPEgsACGyjBN2+gWe26njfvGMB1bAMB4cNUMDJVhmip0q1vszRgy3tq4bwzTsQUAjAd3WABDp7cxZeOlLy5m6Yml1v5B5RZ7bqet+8awHFsAwHgQWAA0xC323I59AwBge4aEADTELfbcjn0DAGB7AguABvV6q0lvNbOdKc+t4AbX9w37BQDArRkSAgAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DoCCwAAAKB1BBYAAABA6wgsAAAAgNYRWAAAAACtI7AAAAAAWkdgAQAAALSOwAIAAABoHYEFAAAA0DrTTX1wKeXrk3wyyfckuSvJO5OsJHk0yetqrddKKT+Z5P6N5W+ttf7LpuoBAIBRM//gh/v+Oxfe+OK+/85BtHMQxqWdsFON3GFRSukkeSjJ1Y1Fb0ny87XWFyWZSfLKUsozkvytJN+Z5OVJ3lZKmWmiHgAAAGC4NDUk5O1Zv6PicxtffyrJwVLKRJL9SZaTfHuSj9Val2qtjyX5dJJvaageAAAAYIjs+ZCQUsprk3yh1vr+UsqbNhb/YZJfTPIzSR5L8sEkr9p4fd3jSZ5+8+fNzc1kevr/b+/Oo+Wo6gSOf7MSdoiCjCMMrj/EIyIMu8SAICAyjsqMcYcYRAVEj8oIzIyKOo77gBsoIC5g8LjMCCLoGBCMKAhGZfuhAsqIKLIalrwsb/64t6V5voRE0t03ne/nnHeSrqru+t2q6lvVv7r31qTVHWbTJk2ayCabrDfoMPpubSy3ZV57rCnlXpU6t7UyGc+KGc+KGc+KGU9vrKnXuX/Nth+WfSbpoXr9ve7FGBazgdGI2AfYHvh8/feZmXl1RBwBfBi4gNLaomND4K6xH7Zw4aIehNi2TTZZj7vuum/QYfTd2lhuy7z2WB3l3myzDR9+oUdoVerc1val8ayY8ayY8azY2hhPa3VuS/6abd/aMSRp9Vhd3+vl1bmrPWGRmX8ehSciLgJeB/w3cE+dfAtl3IrLgPdGxDTKuBZPBa5a3fFIkiRJkqQ1T8+eEjLGHGBuRCwBRoDDMvPWiDgJuIQylsbxmflAn+KRJEmSJEkN62nCIjNndr3cY5z5nwE+08sYJEmSJEnSmqdXTwmRJEmSJEn6q5mwkCRJkiRJzTFhIUmSJEmSmmPCQpIkSZIkNceEhSRJkiRJao4JC0mSJEmS1BwTFpIkSZIkqTkmLCRJkiRJUnNMWEiSJEmSpOaYsJAkSZIkSc0xYSFJkiRJkppjwkKSJEmSJDXHhIUkSZIkSWqOCQtJkiRJktQcExaSJEmSJKk5JiwkSZIkSVJzTFhIkiRJkqTmmLCQJEmSJEnNMWEhSZIkSZKaY8JCkiRJkiQ1x4SFJEmSJElqjgkLSZIkSZLUHBMWkiRJkiSpOSYsJEmSJElSc0xYSJIkSZKk5piwkCRJkiRJzTFhIUmSJEmSmmPCQpIkSZIkNceEhSRJkiRJao4JC0mSJEmS1BwTFpIkSZIkqTkmLCRJkiRJUnNMWEiSJEmSpOaYsJAkSZIkSc2ZPOgAJGmYTZ06iQlTJjNp8kTWWX8dRhcvYWRk6aDD6plOeTdYdwoL71889OWVJElS75iwkKQemTp1EosmTOToL17J5TfdwU5bT+fEWduzzlSG8kf82lZeSZIk9ZZdQiSpRyZMmczRcxdw6Q23s2TZKJfecDtHz13AhCnDmSte28orSZKk3jJhIUk9ssG6U7j8pjseMu3ym+5gg3WnDCii3lrbyitJkqTeMmEhST2y8P7F7LT19IdM22nr6Sy8f/GAIuqtta28kiRJ6i0TFpLUI6OLl3DirO3Z7QmPYvLECez2hEdx4qztGV28ZNCh9cTaVl5JkiT1lh2LJalHRkaWss5UOOUVO6wVT81Y28orSZKk3jJhIUk9NDKyFEaWsu6USSy6d9Ggw+m5TnnXhrJKkiSpt+wSIkmSJEmSmmPCQpIkSZIkNceEhSRJkiRJao4JC0mSJEmS1BwTFpIkSZIkqTkmLCRJkiRJUnNMWEiSJEmSpOaYsJAkSZIkSc0xYSFJkiRJkppjwkKSJEmSJDXHhIUkSZIkSWqOCQtJkiRJktQcExaSJEmSJKk5E0ZHRwcdgyRJkiRJ0kPYwkKSJEmSJDXHhIUkSZIkSWqOCQtJkiRJktScyYMOQBARxwL/AEwFPgl8DzgDGAWuAo7IzGUDC7AHIuIQ4JD6chqwPTATOBFYAnw7M981iNh6JSKmAJ8DtgaWAodRynoGQ7qvI2Id4LPAE4B7gCOARzGk+zkidgHen5kzI+JJjLNvI+IdwIGU8r8pMy8bWMArISI2B64A9qV8V0+mxH49MKeW6TDg8Dr9PZl5bp/iWa/GswhYABzd720cET8B7q4vbwROYczxHRETKXX7M2qsczLzl/2IJzMPjYhJwNnAqZl5fl2uL9tonO3zReA9wGLgD8CrMvO+AcZzOvAhyvf0vMw8oS43kHgy89A6/Xjg6Zk5a5DxAOcAHwRurtPeAVzCgI5n4L2U7/zUuu5ZmXn7mlavDrvWzhstaO1c0YLWzg+taO280AITFgMWETOB3YE9KBffbwU+AvxrZl4UEScDLwC+PrAgeyAzz6D8mCMiPkG5aDwZeDFwA/DNiNghM68cVIw98DxgcmbuHhH7Ui68pjDc+/owYGFm7hoRAXwceAxDuJ8j4hjglcC9ddJffI8j4tfAs4FdgC2BrwI7DSLelVGTbKcA99dJ7wBOyMzzIuJM4MCIuBx4I/D3lAvT70fEdzJzUR/i+TTwxsz8QUS8B3hZRFxDn7ZxREwDyMyZXdMWMOb4piQpp2XmbhGxK/Bhyne9H/E8kZIo3RI4tU7bgT5so+XEk8CMzPx9RLwPmBMR3x9gPFcAB2fmjRFxYUScA0wYVDx1+gHAAcD/1deD3F/vAY7JzK92TXsRgzue5wHHZeYPI+LFwFMiYhFrUL067Fo7b7SgtXNFC1o7P7SitfNCK+wSMnj7AT+n/Eg9BzgX2JHSygLgW8A+gwmt9yLi74GnAXOBdTLzV5k5ClwAPGegwa1+1wOTawZ9I0oGedj39baUcpGZSalMh3U//wp4Udfr8fbtsyh3UkYz8zeU42Gz/oa5Sj5ESSTeUl//BJgeEROADSnH8M7A/MxclJl3A78EtutTPI/LzB/U/8+nbN9+buNnAOtFxLcjYl5EzGD84/tZwPkAmflDykV6P+LZFdiAkji8sGu5fm2j8eKZmZm/r/MnAw8MOJ5darJiA2Bj4PZBxlNbZh0OvLNruUFunx2B2RFxSUR8OCImM7jjeTdgc+CgiLgI2BW4jDWvXh12rZ03WtDauaIFrZ0fWtHaeaEJJiwG79GUCumfgNcBZwITawUG8CfKRdSwOg54F+UH/D1d04ex3Asp2fPrgM8AJwEThnxfLwCeHxET6sloY8p26BiaMtc7kIu7Jo23bzfiwWZ+3dObE6Xb1m2ZeUHX5F9QjttrKS1lLqJPZVpOPDdExLPr/w8C1u9XPNV9lIvz/Sj192frtLHrHhvT0vrDr9fxnAlcnZnXjlmuX9tovHhuA4iIFwJ7AZ8fcDzUuukq4NYa3yDjOYUHm8l3DDKeC4GjgBmU5NfrxomnX8fzWZQbHP9LOXamA68eJ55m69Vh19p5oyGtnSta0Nr5oRWtnReaMKxfgjXJ7cB1mTkCZEQ8QGna07EhcNdAIuuxiNgE2CYzL4yIjShl7RjGcr8ZuCAzj42ILYF5lH64HcNY5tOBp1IueucDP6X8qOwYxjJ3dI9F0innPaw5x/lsYDQi9qGMMfP5+u8zM/PqiDiC0lz1AvpTpvHieRtwbO2Oczmlz28/t/H1wC9rYur6iLib8iNq7LrXGxPTxMzsvvDoVTy3A3/Dg+MPdPRrG40bT0QcDBwM7J+ZD0TEQOOpdzK3rt0f3k45Lw8inqWUpPbZwCbAYyPi7Qx2f30pM28GiIj/oTRhv5vBHM9/BLbOzAtrPOdSxki4jjWnXh12rZ03WtHauaIFrZ0fWtHaeaEJtrAYvO8D+9c70I+l/Jj7bpSxLaD0V7pkUMH12AzKnRIy8x5gJCKeWJsN7sfwlftOHsyG3kEZv+InQ76vdwK+X/vifZ1SEQ/7fu4Yb9/OB/aLiIkRsRXlYuSPgwpwRTJzRmY+u+67BcCrKH1tOy2hbgE2pTTJ3jMipkXExpQE1VV9imdHYHZmHkgZzPU79Hcbz6ZcfFPr7/WAe8c5vudTxrDp3M3/eZ/i2Qj43TjL9WsbjRfPbGBPYJ+udQ4qno2BL0fEpnX+nyiJxkHFswyIeoy/CZiXmf85wHg2Bn4UEY+r859DGUhxUMfzhsAVEbFnnT8DuJo1qF4ddq2dNxrS2rmiBa2dH1rR2nmhCbawGLDMPLf2ZbuMkkA6gjJS7mciYiqlCd1XBhhiLwXlRNbRafo0idIv60cDiap3PgqcHhGXUFpWHAf8mOHe178A3h0Rb6Vkfl8DbMVw7+eOtzBm32bm0rr/L+XB7/uaZA4wNyKWACPAYZl5a0ScRLnYmggcn5kP9CmeXwDnRcR9wIWZeR5AH7fxacAZUQYFG6VcaCxjzPEdZYC5fSPiB5QBHQ/tVzzj3Z3LzCv6tI3GxnM4Jal0JfCtiAA4OzM/NaB4DgU2q7EsoiR35mTmwgHF09r+OpTSDeRrEXE/cA2lO+NSBnQ8UwY1/kRtJn8j8C+ZObKG16vDrrXzxiC0dq5oQWvnh1a0dl5owoTR0dGHX0qSJEmSJKmP7BIiSZIkSZKaY8JCkiRJkiQ1x4SFJEmSJElqjgkLSZIkSZLUHBMWkiRJkiSpOT7WVD0XETOBL1MeiTYKrAucmZkfW8n3Px3YNDMvjoi5wKsyc2Sc5d5OeT7xZasY35GZ+fGI2B/YKjM/vSrvX8Hnvhp4NeURcBOAD2Tmt7vmfwOYkJkH1df7AsfX2bsDP6j/f0tmXjHms88AjgSeBZwA/Ab458xcFhEfBz6UmTfVZU8A5mbmNaujXJIkSZLUDz7WVD1XExavy8xZ9fU6QALbZ+ZdK/H+dwK3ZubJPYrv1szcYjV/5sbAFcC29RnxjwUuoyRElkXElsDngKmUBMwNKxtTRLwE2DwzP1aTHq8C3gWcQUmOzMrM47qW34SSIDpwdZZR0tplTPK54zbgXmAH4A5gHeAq4A2ZuTgiRngw+ToFmAS8FNgT2DUz31A/+xRgt8zcrr4+FNguM9+8nFieBJxIufEyGfgxcGxmLqvzXwKcDjw5M2+p075b178N8Ica73cy872PbMtIUu/VOvhCynXe2V3TfwZcmZmHjPOeacArMvPUVb2erjcC9wGWUW44Htd9Ay0iFgDzM/OI+vqVwGuAacC2wJV10Zdn5m9XrbTSg2xhoUHYkPLDeklEPBt4R52+HuXH9whwDnA7pWI+BBiJiCspF8vbAFsCp1J+8N8HzAI+CMwFtgBeAGwEPBo4ITO/GhEHA0dQWjsAHAwcDkyPiE9SEgrbZObbI+It9TOXABdn5r/Uiv7xwObA3wFvzswLllPGhZTv1+sj4tzM/FVEPLFzMU2p0P8HuB94A/DWVdh+RwEv7FrP+vXvXsq2fEP3wpl5V0Q8EBHbZebPVmE9kjTWvE7yuaO2+DomM8+vr8+i1MFfAe7IzJldyx4OvAV4Lw+t93YCbouIrWvrsJnAWSuI4z+Aj2Xm+RExAfhaXefX6/w5wMeA1wLvBMjM53TFO7cTryStQa6jJH3Phj+3Ql5/BctvQakPT12VlUTEtsA/AHtk5mhEbE+50faMOn8P4OfA3hGxYWb+KTO/AHwhIram1LEzV2Wd0vI4hoX6Ze+IuCgi5gFnAkdl5kLgaZTM797AN4B/qstvATw3MzstBz4ypqvHh4D3ZeZuwCnAM8esbwNgX+C5wEciYjLwFODAWoEmsF+9s3ZH5y4f/Lny/2dKt4zdgSdHxPPr7EWZeQBwNDDunT+AzFxKyUo/GTg/In4NzK6fPxF4GfAFSoLlJRGx7sNtwPredSmtNG6rk94NnATcCDyJcifzpRFxckTs1vXWn1F+AEhSz0TEJEpS+jfLWeTvgDsz83fAaERMr3XudcC3gOfV5XYGvreCVf0aOKReNE+m1Nn/XWN4PDAdeB/wyoiY8shKJUnN+CmwVW09C/AKynU1EXFkRMyLiEsi4tyImErparxtRPx7Xf4FEfHdiFgQEQetYD1/ALYCZkfE32bmAkq93HEYJSn9dUr3Z6lnTFioX+Zl5szM3Dsz98vM8+r03wIn1Ttee1GaDAPcON44FV0CuBQgM7/cPTZE9b3MXJaZvwfuBDajVL6fi4jPAtt1rWusbYAfZubizBwFLqEkVgB+Uv+9mdLkbfzgSheQdTPzyMx8MiV58rZ6Yb4f5YL+LEqLkU4CY2VsCvyx8yIzr83MFwP/SWm1cVb9/COBf+t63++AR63kOiRpeTrJ587f2+r0D0TERcC1wGMoSWEoLdguiogra+J2GvD+Ou+7wB7AAZRkxbeAA2rC4abMfGAFcfwr8ENKUuIPwGeBjeu81wCnZ+bdlPPEix5xqSWpHV8DXlhbl+1MuVk1kXKdt09m7km5xt2J0prtmsw8ob73t7W12ZuA1y9vBZn5R2oLC+DSiLgOeD5ARGxEGUPtm5Sud8v9HGl1MGGhQTsVOLT2u7uFB7trLOtaZhl/eaxeS6mIiYiXR8RRY+bvWOc9htI15D7KOA+zKE3j7u9a14Qx770O2CUiJteTwQzg+jpvZQd92QI4MyI2ra9/TUk0jNT1z8nM/TNzf8qdwSNW8nNvpyQ7xnotpSUKlG01ykObCG5KuaiXpEeik3zu/H2wTj+mvn4KcD7w4Tq90yVkJ+BiYKS2rgP4DmUsi/2A8zPzauBxlNZgD9ddY6/M/K/MnEHpIrgQ+LfawuMVwMERcT6lZd2Rj7zYktSMsyjXszMoN9WgXCuPAF+KiNModel4N+Y6Y1DcSumKPa46TtA9mTk7M7ei1KufiojpwMsp15rnAh8H/iYinvOISyUthwkLDdoXgB9FxHzKD/HHjrPMFcCREbFX17S3AcfWO3ovpzaH67JFHWDtm5QxHe4B5lMGALqEkrDorOuaiPhi542Z+XNKy4f5lHEtbqI2NV5ZmXklpavGvFq2iynJmTuBXYALupadD0yLiN1X4nMXAbdGxOadaTXTPTMzz8nMOyknofnAaV1v3YVyN1OSeu1myvhCf1a7yb2WclewMwDw94DdgKld3dwuo7SQeLiExQfqk5WoCZDrgUWULiWXZ+ZeNSm8M/CYiNhuNZRLkgauDtS+PvBGoHP9uhHwj5n5EspYZxMpN+TG3vRb2Rtv21ESFJ3WxNcDd1PGoJsDHNR14+0oVv7Gm7TKfEqIhk5EHEIdPHPQsfRCRLwU2CIzP7qSy08HPtd5fKok/TWW85QQgN8DT6U8dWMp5UkcszPzhrFPPIqIPSkDtz09M++t4xpdnJnvrPP/EfhoZj7+YWJ5KiUpvCnlruINlGbJZwKnZuY3upY9BnhSZr62vj4DB92UtIaJrqfu1ZbFr8zMnSNif8o4aY+mJC4W1b/TgK9Sus9dQLlZd2tmnhwR2wAnr2hgzIg4ntIKeCEl6fF+Sovh0zJzh67lplHGLdoxM2/uGnRz19VZfq29TFho6PQzYVEHMdp7nFmHZuaNPVrnBODzwOu7mlavaPl3A1+uLUckSZIkaY1gwkKSJDUnInYGPjDOrLMz81P9jkeShk1EfBLYdpxZB2Tm/f2ORxqPCQtJkiRJktQcB92UJEmSJEnNMWEhSZIkSZKaY8JCkiRJkiQ1x4SFJEmSJElqjgkLSZIkSZLUnP8H7vw4fS8jZOoAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "sns.pairplot(df_total_new[['Participation_SAT (%)', 'EBRW_SAT', 'Math_SAT']], size=5)" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "sns.pairplot(df_total_new[['Participation_ACT (%)', 'Math_ACT', 'Science_ACT','Verbal_ACT',]], size=5)\n", "# point are too small though (don't know yet how to increase them)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 2) Old ones:\n", "\n", "I plotted just for the SAT to avoid excess repetition." ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5,1,'Participation_SAT (%)')" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'SAT Math')" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'SAT Evidence-Based Reading and Writing')" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import seaborn as sns\n", "\n", "fig, axs = plt.subplots(1, 3, figsize=(12,6))\n", "\n", "axs[0] = sns.distplot(df_total_new['Participation_SAT (%)'], kde=False, color='blue', ax=axs[0], bins=10)\n", "axs[1] = sns.distplot(df_total_new['Math_SAT'], kde=False, color='red', ax=axs[1], bins=10)\n", "axs[2] = sns.distplot(df_total_new['EBRW_SAT'], kde=False, color='green', ax=axs[2], bins=10)\n", "\n", "\n", "axs[0].set_title('Participation_SAT (%)', fontsize=8)\n", "axs[1].set_title('SAT Math', fontsize=8)\n", "axs[2].set_title('SAT Evidence-Based Reading and Writing', fontsize=8)\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 19. When we make assumptions about how data are distributed, what is the most common assumption?" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "That they are normally distributed." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 20. Does this assumption hold true for any of our columns? Which?" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "No. In fact some of the distributions seem to be bimodal (two peaks in the distribution). " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 21. Plot some scatterplots examining relationships between all variables.\n", "\n", "I will make several plots and make the commentaries after them." ] }, { "cell_type": "code", "execution_count": 48, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_total_new.plot(kind='scatter', x='Participation_SAT (%)', y='EBRW_SAT', c='blue', title='Participation_SAT (%) vs EBRW')" ] }, { "cell_type": "code", "execution_count": 49, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEPCAYAAABIut/fAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzt3Xl8XGXZ//HPdBJCSocWk8iioRWBC63ygHH5AVIqDyiIUq1V+SGLC5tSLBWVRaqCLC5AWaSyFhRBsLUI+HtQdkQWlVIERC5AoFZ9gKZQSGRos8zvj/sEpukkcxLmZCYn3/frxYvOPWe555r2mvtc55z7ZAqFAiIikj7jqt0BERFJhhK8iEhKKcGLiKSUEryISEopwYuIpJQSvIhIStVVuwNSeWY2Bfg78HBRcwY4x90XDnFb+wAfcPdvm9m+wB7u/tVBlr8EuNrdbxl6z8HMDgE2cPcFZnYEMMndvz+cbZXZz+bA2cA7gQKQB05z9+v6LfcrYDdgS3d/JWo7CPhatMiW0boro9dHuftdJfZ3BfAD4HHg18C2wK3ufnj0/tuBC919j6J1PgG8292/V5EP/fp2DwaOd/ft+rVvCjwFbOXuz8Xc1hTgEXefMMQ+PAPMcvf7h7KeDI1G8OmVd/cd+v4DPgqcaWbbD3E77wPeBODu1w+W3KNlDhluco98EBgfbeuCJJJ75BLgPnd/t7tvD3wBuNzM3tG3gJltAUwD7gMO6mt3958VxfV6YH5RrEsl988AL7n7I8BewAp33xqYbGbvihY7CzimeD13/zUwzcx2qODnBrgGaDazXfq1fxG4Lm5yl9qnEfwY4e7/MrMngG3N7O/AT4BtgCagA9jf3d3M7gBeALYjJIIjgKyZvQQ8QRh1fczMNgMuiJbrBS5w93Oj9X8M3A/cCfwW+ADhCGK2u98VjRQvBDYFNgOWA58BdgH2BfY0szzQAjS7+2wzmxptt4kw4j7T3X9mZtOBUwkjz3cB9cDh7n53mZBsDjSa2Th373X3R6MjlBeLljkMuBVYDHzPzC509+HcGXgS8Onoz2uAjcxsA8IP2Voz+xgh6f+lxLqXAt8BPlncaGZXAUvd/czo9ZeB6cCXgMsI320vsJQQj96+dd39VTNbSEjod0frZ4BDgAOj128hxHtLQkyvdvfTohH7XcDfgCnAwcC46MitDegCvuru9w30Pbv780OMnwyTRvBjhJntBGwN/BHYG1jt7ju5+7bAn4HZRYu/6O7vdPeTCEn8Gnf/Vr9NLgAejw7zdwIOM7Ot+y2zJXBnNNI9DrjGzOqB/YB73X0nYCvgFeBAd7+W10fE5xf1vS5qPy8abe8NnBZ9Jgg/IGe6+46E5HZajJB8PfrMz5vZdWb2DeApd3+2aJ+HAj8HbiAkqb1ibHcd0Qi9MRq9A9wMvAo8CNxOSHonAvMG2MRNwN5m1tiv/WLg80WvPx+1fRLIRTF/X/TeViW2+xNglpn1lVb2AF5293ui11cAC929DXg/sEd0JALwVuB70d+d/wUagZuj+J8ILIp+wEp+zwN8TkmAEnx6NZrZg9F/jwCnA59z9xXuvphQjjjKzM4hjPyKa6jrlRlK2AO4CMDdX3L3d7n7k/2WedHdr4qWuRHoAbZ393OAe8zsa4Qfinf1239/2wIbuvuSaFv/Bn7F6wl3ubs/GP35AaKS0mDc/TbCD9AnCD96HwceM7O+pDgDyAK/dfc1wNXA0eW2W8J2wGtxiY4WDol+QL8DfJMwSm82s2vN7DdmtmPR8i8QfhAm99vuHcCGZvZeM3sn4WjnVuAPwNToSOo44OwS3wvu/nS0bF/SPowwYsfMNiKcd/iemT1IKFFtCfSVirqBe4s2t9rdr4m2e1Pf5x7G9ywVphJNeuWjUdx6osP5vn/QVxFKMm8rWqQzxva7CaWSvm1uBbSXWKbYOKDHzH5AGBUuJIxi6wklnIFki/dVtK366M/5ovZCmW1hZm8Gvks4IfoHQqI7LSozHEw4ovkKYWT6pJkBbABsbmZT3f2vg22/nwIDDKTMbEvCD+WHCEcKZwFPA78Adi1atJvw4/gady+Y2aWEcwNrgEuj8tHT0ZHUdGB34BYzO8zdbyjRhQXACWZ2Q7S/vvMMWUIMdy46sdxM+KFpBta4e/F3u07fos/bNYzvWSpMI/ix6SPA5e5+KeCE0Wt2gGW7eT2RFruFcGISM5tIGD1u02+ZFjPbK1rm44T67MPR/s929yuA54E9i/Zfan+PERLGzGhbWwCfIpQ7huOFaJ9zotozZjYeeDvwgJltSxjBtrn7lOi/LYDfA3OGuC+PtlvKmcCxUX28gfDZe4lOMkf9mghsCPyjxPqXE85ZfJpQmur78b4MuMndjwV+B7xngP3fSKiNfwv4ubvnAdz9ZcKo/WvRNicRavUzBthOU3Qeoe97zhPO1wz2PcsIUIIfm84ADjezhwjlmAcI9flSbgM+Ymbn9WufDbwj2sbdwOnuvrTfMq8CB5rZXwhJ5BPu3gOcDJwRrXs9YQTdt/8bgSPM7Pi+jbh7F6GUMida5xbgZHe/fRifnWj0+WHCuYOnoxLWH4HfRJeRfhm4tkRp4+To8zQPYV+PAPniq3MAzGwPoNPd74uaziQk5ttZtx7/4ahfa0ps+1nCd/dQVLYC+BkhiT5qZkuBicC5A/Stl3COZTahJl9sf+D/mNnDhNj8wt2vHOBjPg98KirnHA98KorxYN+zjICMpguWJAz3+ug0MrP9gQ+6+1eGse5twNHu/lDleyZppxq8pFJ0VcznBnj7R4OMRivO3a8ys33N7N3u/nD5NQIz+yRwl5K7DJdG8CIiKaUavIhISinBi4ikVMVr8NGdigsJtzE3AKcQLrm6GNiEcIb/IHf/e6X3LSIir0viJOsBwCp3P9DMmoBlhEvtrnT3X5rZhwh3962X4Feu7BhTJwQmTGigs3O9q9+kH8UpHsUpnjTGqaUlV/IGsiQS/CLC5Ex9ugmTSD1kZrcAzzD0m0VSqa5O93zEoTjFozjFM5bilNhVNGaWI9zccDHwU+Awd7/MzL4N1Ln7t/uvk8+vLYyl4Gez4+jp6S2/4BinOMWjOMWTxjjV12dHbASPmbUC1wILomuAzyIkewgz851aar20HTaVM2nSeFavfqXa3ah5ilM8ilM8aYxTS0uuZHvFr6KJ5oC+iTDHRt/Tg/5AeOAEhAcoDGWyJhERGYYkRvAnEK6WmWdmfXNqHAxcEk2E9BJhngsREUlQxRO8u8+h9EnUPSu9LxERGZhudEpIpr2dumVLybT3nyJdRGRkKMEnoGHJIprapjJx1gya2qbSsGRx+ZWqQD9CIummBF9hmfZ2cnNnk8nnGdfxMpl8ntzcI2suiY6WHyERGT4l+ArLrlhOoW7dBxIV6urJrlhepR6tb7T8CInIG6MEX2E9rZPJdHet05bp7qKntf8zk6sn7o+QSjgio5sSfIUVmpvpmH8+hcZGenMbU2hsDK+bYz/lLXFxfoRUwhEZ/WrqgR9pmmws095OdsVyelonD5jcq3lHXcOSxeTmHkmhrp5Mdxcd889nzcxZQOh7U9tUMvn8a8sXGhtZtfSvVfmhSuOdh0lQnOJJY5xGcrIxIYzku2to1N7fmpmzWDtteskfob4SToaiBB+VcGr5M4nIupTgx7CBfoRGw3kEESlPNXhZz2g4jyAi5WkELyUNVsIRkdFBCV4GVOvnEURkcCrRiIiklBK8iEhKKcGLiKSUEryISEopwYuIpJQSvIhISinBi4ikVCLXwZtZPbAQmAI0AKcA/wRuAJ6IFvuJu1+TxP5FRCS5G50OAFa5+4Fm1gQsA04GznL3MxPap4iIFEkqwS8CiicQ7wbaADOzGYRR/NHu3pHQ/kVExrxE54M3sxxwPXAxoVTzkLsvNbNvAZu4+9eLl8/n1xbq6rKJ9afWZLPj6OnprXY3ap7iFI/iFE8a41Rfnx3Z+eDNrBW4Fljg7leZ2SR3Xx29fS1wXv91OjvXJNWdmpTGBw8kQXGKR3GKJ41xamnJlWxP5CoaM9sUuAk41t0XRs2/M7P3R3/+b2BpEvsWEZEgqRH8CcAmwDwzmxe1fQ0428zWAs8ChyW0bxERIaEE7+5zgDkl3to5if2JiMj6dKOTiEhKKcGLiKSUErzEkmlvp27ZUjLt7dXuiojEpAQvZTUsWURT21QmzppBU9tUGpYsLr+SiFSdErwMKtPeTm7ubDL5POM6XiaTz5Obe6RG8iKjgBK8DCq7YjmFuvp12gp19WRXLK9Sj0QkrlQkeNWHk9PTOplMd9c6bZnuLnpaJ1epRyIS16hP8LVaH07Lj06huZmO+edTaGykN7cxhcbG8Lq5udpdE5EyEp1sbKhWruwYUmcy7e00tU0lk8+/1lZobGTV0r9WNQE1LFlEbu5sCnX1ZLq76Jh/PmtmzlpvudE0J0amvZ3siuX0tE4e8diOpjhVk+IUTxrj1NKSKznZ2KgewddifTitJyULzc1079imkbvIKDKqE3wt1oeH86OTlnKOiNSWUZ3ga7E+PNQfnWqeQ9APi0i6jeoafJ9q1odLaViymNzcI8vX4Lv+Q93WW1XlHELc8wS1II010yQoTvGkMU4D1eATe+DHSCo0N9NdA4m9z5qZs1g7bXrZH53M8mdCgqUowUflnCQ/T/F5gr595+Yeydpp02viB1JEKiMVCb4WxfnRKUyeUpVzCH3nCcr9sNTakZGIDM2orsGPei0tVTmHEOc8Qa3eXyAi8aWiBj9a9dUCqzFSHuw8Qa3dX5DGmmkSFKd40hinVNfgR7tqnEMY7DxB3BKOiNQ2lWhkPbV4f4GIDF3FE7yZ1ZvZFWZ2l5n9ycz2LXpvfzO7t9L7lKEbrMZei/cXiMjQJVGiOQBY5e4HmlkTsAy43sx2AL4ElKwVyciJc5lk3Es9RaR2JVGiWQTMK3rdHSX67wNHJ7A/GaK40ykMZf4Z3RUrUnsqPoJ3904AM8sBiwnJ/lJgLhSdtZOqqXSNfTTdFSsyliRymaSZtQLXAguAR4DLgJXAhsA7gYXuvt5oPp9fW6iry1a8P7Uqmx1HT09vVfadueZqsocdCvX10NVFz0UXU/jsfkPf0MqVJadb6H7yKWhpqUhfqxmn0URxiieNcaqvz47MZZJmtilwEzDb3W+NmqdG700Bri6V3AE6O9dUujs1rarX435kX8bdbNQ/cD9d73kvvdsaDKMvdY88xsQSl1R2PvIY3TtuVJGupvG65SQoTvGkMU4tLbmS7UmcZD0B2ASYZ2Z9tfi93V3lmWFK4kaoSpVVdEmlSO3SnaxVFGckkUR9u9J3qsadPXO40jjiSoLiFE8a46Q7WUehpGZ9rPSdqrqkUqQ2KcHXsKSmDEiirFJrUzaLiKYqqGlJ1bd1p6rI2KARfA3rS8T969uVSMQqq4iknxJ8jUsyEausIpJuSvCjgBKxiAyHavAiIimlBC8iklJK8CIiKaUELyKSUkrwIiIppQQvIpJSSvAiIimlBC8iklJK8CIiKaUELyKSUkrwIiIppQQvIpJSSvAiIimlBC8iklIVny7YzOqBhcAUoAE4BXgSuAjIAH8BjnL3nkrvW0REXpfECP4AYJW77wrsDfwYOA04wd13AcYD+yawXxERKTJogjezzYexzUXAvKLX3cCn3P33ZrYBsBnw3DC2KyIiQ1CuRHMlsPtQNujunQBmlgMWAye6e4+ZTQZuAV4CvNS6EyY0UFeXHcruRrVsdhyTJo2vdjdqnuIUj+IUz1iKUyKP7DOzVuBaYIG7XwXg7suBbczsEOAs4OD+63V2rkmiOzVr0qTxrF79SrW7UfMUp3gUp3jSGKeWllzJ9nIJvs3M7unXlgEK7r5zqRXMbFPgJmC2u98atV0PHOPuTwAdQO8Q+i5VkmlvT+Rh3yIyMsol+EeB/zvEbZ4AbALMM7O+Wvy3gMvNbC3wCnDIELcpI6xhySJyc2dTqKsn091Fx/zzWTNzVrW7JSJDkCkUCgO+aWa3u/uHRqozK1d2DNyZFKrVQ8VMeztNbVPJ5POvtRUaG1m19K9VGcnXapxqjeIUTxrj1NKSy5RqL3eZ5KUJ9EVqXHbFcgp19eu0Ferqya5YXqUeichwlEvw15jZaWa2IYCZ7WNm3zezRE7OSm3oaZ1MprtrnbZMdxc9rZOr1CMRGY5yCX4+0MjrJ0XvJdyodFaSnZLqKjQ30zH/fAqNjfTmNqbQ2Bhe60SryKhS9ioad9+p74W7v2Bmc4A/JtstqbY1M2exdtr0YV1Fo6tvRGpDuRF8vn+DuxeA/yTTHaklheZmundsG1KSbliyiKa2qUycNYOmtqk0LFmcYA9FZDDlEvxKM3tvcUP0Ol2noKUiMu3t5ObOJpPPM67jZTL5PLm5R5Jpb69210TGpHIlmmOA68zsH8BTwJaEWSI/k3C/ZBTqu/omU3Tg13f1TbdKNSIjbtARvLv/E3gf4WTrnwknV98P/G/yXZPRZrhX32Ta26lbtlQjfZEKKztdsLv3uvvv3f1qwiyQZwC6IFrWM5yrb1SzF0lOrOvZzeyjwGxgF+D7wA5JdkpGr6FcfVNcs+8r6+TmHsnaadN19Y1IBQya4M3sGODzhKcwnQmMc/fTR6BfMooVmptj1dxVsxdJVrkSzdeBm4EfRDNDahZIqRjdMSuSrHIJfgpwP3COmd0HtJrZxMR7JWOC7pgVSdags0kWM7OtCdP87gfc7+4VnztWs0mOTeXufFWc4lGc4kljnIY7m+Rr3P1Jdz8OeDvhUX6Y2eGV6Z6MZcO5Y1ZEyhvyrJDu3kN4HB/AZ4ELK9ojERGpiNgj+AGUPCwQEZHqe6MJfkzVzEVERpM3muBFRKRGvdEnM61XojGzemAh4RLLBuAU4B/AeUAPsAY4yN2fe4P7FhGRQZS7k3Xbgd5z98eBb5Z46wBglbsfaGZNwDLgaeAod38wuvLmWOBrw++2iIiUU24EP9AVMgVgd3f/c4n3FgHFM0Z1A/u5e98MlHXAq0PqpYiIDFnsG52KmdkG7r62zDI54HrgYne/KmrbGbgUmObuK/uvk8+vLdTVZYfcn9Eqmx1HT49mfyhHcYpHcYonjXGqr8+WvKIx7myShxNKKvWEunsXMGD5xsxaCdfKLyhK7p8FvgXsUyq5A3R2ronTndRI4x11SVCc4lGc4kljnFpaciXb415FcygwHbgR+ALw6EALmtmmwE3Ase6+MGo7gDDd8HR3fyp2r0VEZNjiJvj2qIaec/c7gDcNsuwJwCbAPDO7w8zuIlxBkwOWRG0nvZFOi4hIeXEvk3zJzD4BFKJyTctAC7r7HGBOJTonIiLDF3cEfwjwDHAcofb+5aQ6JCIilRF3BL8W2JWQ3B8B7kqsRyIiUhFxR/A/Bd4C3AJsQ7hTVUREaljcEfxm7r5f9OfrzOzOpDokIiKVMegI3sw2MLMNgGfM7H1R2/bA4yPRORERGb5yI3gnTEuQAXYzszWECcQ01YCISI0bNMG7+9sg3Kjk7j8fmS7JSCn3LFRJnr4DSdJQ7mSVFGlYsoimtqlMnDWDprapNCxZXH4lqSh9B5K0WJONmdl9hNKMA70A7r5/pTuzcmXHmHpCVLXmxMi0t9PUNpVMPv9aW6GxkVVL/1qTo8g0zh2SxHeQxjglIY1xamnJDX+yMcL87ZIS2RXLKdTVk6EoudTVk12xnO4aTPBppO9ARkLcEs0DwJ7AQUAT8K/EeiSJ62mdTKa7a522THcXPa2Tq9SjsUffgYyEuAl+IfAU4U7WZwlzussoVWhupmP++RQaG+nNbUyhsTG81shxxOg7kJEQt0TT5O4Lo6tp7jGzkvUeGT3WzJzF2mnTdQVHFek7kKTFfui2mW0X/f+thIdnyyhXaG5WvbfK9B1Ikso9dPuLwC+ArwKXAe8gPG/1K8l3TURE3ohyI/jtCQ/wuAn4srs/mHyXRESkEgY9yeruRxNG7bcBp5rZ3Wb2JTMbPyK9ExGRYStbg3f3LkJZZrGZbU54WtM/ABUORURqWKyTrGa2IfBJwnXwOeCbSXZKRETeuHInWacDBwPTgeuAb7j7I8l3S0RE3qhyI/iTgAuBI9x9TZwNmlk94caoKYT5a05x9+uj9+YD7u4XDLvHIiISS7npgncbxjYPAFa5+4Fm1gQsM7N7gZ8R7oT90TC2KSIiQxT7RqchWEQ4KdunG5gAfBfYO4H9iYhICRVP8O7eCWBmOUKiP9HdnwaeNrNBE/yECQ3U1WUr3aWalc2OY9IkXXFajuIUj+IUz1iKUxIjeMysFbgWWODuV8Vdr7MzVpk/NdI4L3USFKd4FKd40hinlpZcyfaKJ3gz25Rw5+tsd7+10tsXEZF4khjBnwBsAswzs3lR297unh9kHRERqbBYj+wbKXpkn5SiOMWjOMWTxjgN9Mi+uA/8EBGRUUYJXkQkpZTgRURSSgleRCSllOBFRFJKCV5EJKWU4EVEUkoJXkQkpZTgRURSSgleRCSllOBFRFJKCV7GjEx7O3XLlpJpb692V0RGhBK8jAkNSxbR1DaVibNm0NQ2lYYli8uvJDLKKcFL6mXa28nNnU0mn2dcx8tk8nlyc4/USF5STwleUi+7YjmFuvp12gp19WRXLK9Sj0RGhhK8pF5P62Qy3V3rtGW6u+hpnVylHomMDCV4Sb1CczMd88+n0NhIb25jCo2N4XVzc7W7JpKoRB66LVJr1sycxdpp08muWE5P62QldxkTlOBlzCg0N9OtxC5jSCIJ3szqgYXAFKABOAV4FLgcKACPAEe6e28S+xeR0SXT3q6jqwQkVYM/AFjl7rsCewM/Bs4CTozaMsCMhPYtIqOI7lFITlIJfhEwr+h1N9AG3Bm9vhHYI6F9i8gooXsUkpVIicbdOwHMLAcsBk4EznD3QrRIBzCx/3oTJjRQV5dNoks1KZsdx6RJ46vdjZqnOMUzGuOUefI5qK+HfP71xvp6Jq1+jsLWWyayz9EYp+FK7CSrmbUC1wIL3P0qM/th0ds5YHX/dTo71yTVnZo0adJ4Vq9+pdrdqHmKUzyjMU6ZSZvS1LXuPQp0dbF60qYUEvosozFO5bS05Eq2J1KiMbNNgZuAY919YdS8zMymR3/eG7griX2LyOihexSSldQI/gRgE2CemfXV4ucA55rZBsDfCKUbERnjdI9CcjKFQqH8UiNk5cqO2unMCEjjoWISFKd4FKd40hinlpZcplS7pioQEUkpJXgRkZRSghcRSSkleBGRlFKCFxFJKSV4EZGUUoIXEUkpJXgRkZRSghcRSSkleBGRlFKCFxFJKSV4EZGUUoIXEUkpJXgRkZRSghcRSSkleBGRlFKCFxFJKSV4EZGUUoIXEUmppB66jZl9APiBu083s/cAFwBrgAeBOe7em9S+RUQkoRG8mX0TuATYMGq6CDja3XcFXgL2T2K/IiLyuqRKNH8HZha9fqu73xP9+W7ggwntV0REIomUaNz9V2Y2pajpKTPbzd3vBD4ObFRqvQkTGqiryybRpZqUzY5j0qTx1e5GzVOc4lGc4hlLcUqsBt/PF4BzotLNnwm1+PV0dpZsTq1Jk8azevUr1e5GzVOc4lGc4kljnFpaciXbR+oqmn2AL7r7PkATcPMI7VdEZMwaqQT/BPA/ZnYP8LK7/88I7VdEZMzKFAqFavfhNStXdtROZ0ZAGg8Vk6A4xaM4xZPGOLW05DKl2nWjk4hISinBi4iklBK8iEhKKcGLiKSUEryISEopwYuIpJQSvIhIlWXa26lbtpRMe3tFt6sELyJSRQ1LFtHUNpWJs2bQ1DaVhiWLK7ZtJXgRkSrJtLeTmzubTD7PuI6XyeTz5OYeWbGRvBK8iEiVZFcsp1BXv05boa6e7IrlFdm+EryISJX0tE4m0921Tlumu4ue1skV2b4SvIhIlRSam+mYfz6FxkZ6cxtTaGwMr5ubK7L9kZoPXkRESlgzcxZrp00nu2I5Pa2TK5bcQQleRKTqCs3NdFcwsfdRiUZEJKWU4EVEUkoJXkQkpZTgRURSSgleRCSlauqZrCIiUjkawYuIpJQSvIhISinBi4iklO5kHQFmVg8sBKYADcApwKPA5UABeAQ40t17q9TFmmNmbwaWAnsC3ShW6zGz44F9gQ2ABcCdKE7riP7t/ZTwb68HOJQx9PdJI/iRcQCwyt13BfYGfgycBZwYtWWAGVXsX02J/lFeCOSjJsWqHzObDuwM7ALsBrSiOJXyUaDO3XcGTgZOZQzFSQl+ZCwC5hW97gbaCCMugBuBPUa6UzXsDOAC4N/Ra8VqfR8BHgauBW4AfoPiVMrjQJ2ZjQM2BroYQ3FSgh8B7t7p7h1mlgMWAycCGXfvu0a1A5hYtQ7WEDP7PLDS3X9X1KxYra8ZeC/waeAI4EpgnOK0nk5CeeYx4GLgXMbQ3ycl+BFiZq3A7cAV7n4VUFzzywGrq9Kx2vNFYE8zuwPYAfgZ8Oai9xWrYBXwO3df6+4OvMq6iUpxCuYS4rQt8F+EevwGRe+nOk5K8CPAzDYFbgKOdfeFUfOyqI4KoS5/VzX6VmvcfZq77+bu04EHgYOAGxWr9fwB2MvMMma2BbARcKvitJ4XgZeiP78A1DOG/u3pTtYRYGbnAJ8lHCb2mUM4XNwA+BtwqLv3VKF7NSsaxR9BONq5GMVqHWb2Q+BDhIHaCcDTKE7rMLMJhCvYNifE5RzgfsZInJTgRURSSiUaEZGUUoIXEUkpJXgRkZRSghcRSSkleBGRlNJkY5K46JrjXxImWCsAjcCV7n5ezPXfDWzi7r83s6uBg9x9bYnljgNuc/c/DbF/s939x2a2F7Clu180lPXLbPuzhMv0tnH3fxe1f4JwqWyGEI8fuftiM7sSeAvh7su1hOkaHnb3o/ptd1fgPcB5wBLCZYAnuvvNZrYVMMfd50TLbha9N7tSn0tGB10mKYmLEvwR7r5f9LoBcGAHdy97F6GZfRd41t0vSKh/z7r7Zglt+2bCrJivuvt3o7adgdOBfdy908yagPuAGe7+aLTMdxngM5tZBriFcJPOuwg3g50EXO7uM8xsIXC8uz9XtM7pwG/d/c7+25P00gheqiFHmLq128x2A74TtY8nJKv554VVAAADYklEQVS1hAm0VhGmd/g8sNbMHiAcCWxHmD3xEsLNKq8A+wE/Aq4GNiPMELgxYc6Wk939V2Y2CziSMGoGmAUcDrzJzBYAfwK2c/fjzOyYaJvdwO/d/dgo6b6NMHXCZGBuvzlz1mFmbwPeREjmD5jZqe7eRZiy9mx37wRw91Vm9n7i3zK/J/Cou681s07CXawbAf8xs12AJ4qTe+Qqwo+AEvwYohq8jJTdzewOM7uNMDHWUVGCmwoc4O67A9cTJs+CkKQ/7O4nEebuPqtf6eUM4HR334kwtfCO/fY3gZAIPwycZWZ1wLaEUfN0whHER9z9VOAFd/9K34pRSegzhOl4dwa2MbOPRW+vcfe9CeWVuWU+85eAhe7+EnAvMDNq3wJ4qnhBd3+xaAKscqYDD0XrPQ78EzibMB3u0cA1ZvYTMzstmkURQnlsl5jbl5TQCF5Gym19JZp+/gWcG41E3wLcHbU/XarOXsQISRN3/yWAme1f9P6d0UMcnjOzF4EW4Hngp9G+tutbv4TtgPui0TZmdhfhhwhgWfT/FcCGA3bOLEt4DsDTZvZxwkh+NnANsJxwBPKXouV3AZ5z9ycH+cx9mgklHQCiH8G+z38d4QjhUsIPwX8DN7t7j5l1m9m4tD7cQtanBC/VdgmwVTSd8k95vXxSnIR6Wf9o82/A+4BbzOxzhARarA1em+htY0IZ5yRgy+j9m4v2lem37mPAMdGovweYRpjV8r8IJ4nj+CjwZ3fvOyLBzB43s+2By4Dvm9nt7v6f6OlVlxFKRnE8D0wqbjCzDYFPRds4O+p3gXAk01e371ZyH1tUopFquwL4o5ndTajNb1FimaXAbDP7UFHbN4DjownJPkco+xTbzMxuBf4f8BXgZcLRwQOE2QPzRft61Mx+3reiuz9MqPXfTajLPwP8eoif69DosxW7BJjt7vcCFwE3m9mdhId1HO/uD8Xc9h3AB/q1HQ2cG5V5LiM8MGUvwiymAO9m4CMWSSldRSOpEz00ZDt3P67afUlCVFe/jXCOYrAyVvE6PwRucPfUTo0r61OJRuQNMLNvA7uXeOsL7v50Evt0914zO4lwZHJ2ueWj6+A3VnIfezSCFxFJKdXgRURSSgleRCSllOBFRFJKCV5EJKWU4EVEUkoJXkQkpf4/m2o4M0317p8AAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_total_new.plot(kind='scatter', x='Participation_ACT (%)', y='Verbal_ACT', c='red', title='Participation_SAT (%) vs Verbal')" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_total_new.plot(kind='scatter', x='Participation_SAT (%)', y='Math_SAT', c='red', title='Participation_SAT (%) vs Math')" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_total_new.plot(kind='scatter', x='Participation_ACT (%)', y='Math_ACT', c='red', title='Participation_ACT (%) vs Math')" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,0,'Rate')" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'SAT correlation between Math and EBRW scores')" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "(50, 105)" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "(450, 600)" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_aux = df_total_new.copy() # To backup\n", "plt.scatter(df_aux['Participation_SAT (%)'],df_aux['Math_SAT'], color = 'r', label='Math')\n", "plt.scatter(df_aux['Participation_SAT (%)'],df_aux['EBRW_SAT'], color = 'b', label='EBRW')\n", "plt.xlabel('Rate')\n", "plt.title('SAT correlation between Math and EBRW scores')\n", "plt.grid(True)\n", "plt.xlim([50,105])\n", "plt.ylim([450,600])\n", "plt.legend(loc='upper right')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Same plot as above with different $y$-range show the negative correlation more clearly:" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,0,'Rate')" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'SAT correlation between Math and EBRW scores')" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "(50, 105)" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "(400, 650)" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(df_aux['Participation_SAT (%)'],df_aux['Math_SAT'], color = 'r', label='Math')\n", "plt.scatter(df_aux['Participation_SAT (%)'],df_aux['EBRW_SAT'], color = 'b', label='EBRW')\n", "plt.xlabel('Rate')\n", "plt.title('SAT correlation between Math and EBRW scores')\n", "plt.grid(True)\n", "plt.xlim([50,105])\n", "plt.ylim([400,650])\n", "plt.legend(loc='upper right')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 54, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,0,'Rate')" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'ACT correlation between Math and Verbal')" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(df_aux['Participation_ACT (%)'],df_aux['Math_ACT'], color = 'r', label='Math')\n", "plt.scatter(df_aux['Participation_ACT (%)'],df_aux['Verbal_ACT'], color = 'b', label='Verbal')\n", "plt.xlabel('Rate')\n", "plt.title('ACT correlation between Math and Verbal')\n", "plt.grid(True)\n", "plt.legend(loc='upper right')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 22. Are there any interesting relationships to note?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "- Participation rate and scores seem to be \"universally\" negatively correlated. A larger fraction of students taking the tests is correlated with lower average grades for all tests in both SAT and ACT. This may have several explanations. One of them could be lack of incentive from public schools, in some states, for students to take the exams. Tesk takes would then come mostly from private schools which tend to score better. This issue must be investigated in much more detail and there are a multitude of articles online discussing the topics.\n", "\n", "- Good or bad performance in Math and Verbal tests seem to occur together i.e. student on average do well in both or in neither. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 23. Create box plots for each variable. " ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for Participation_SAT (%)')" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for EBRW_SAT')" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for Math_SAT')" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig = plt.figure(figsize=(12,4))\n", "\n", "ax1 = fig.add_subplot(131)\n", "plt.boxplot(df_aux['Participation_SAT (%)'])\n", "ax1.set_title('Box plot for Participation_SAT (%)')\n", "\n", "ax2 = fig.add_subplot(132)\n", "plt.boxplot(df_aux['EBRW_SAT'])\n", "ax2.set_title('Box plot for EBRW_SAT')\n", "\n", "ax3 = fig.add_subplot(133)\n", "plt.boxplot(df_aux['Math_SAT'])\n", "ax3.set_title('Box plot for Math_SAT')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for Participation_ACT (%)')" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for Verbal_ACT')" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "{'boxes': [],\n", " 'caps': [,\n", " ],\n", " 'fliers': [],\n", " 'means': [],\n", " 'medians': [],\n", " 'whiskers': [,\n", " ]}" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "Text(0.5,1,'Box plot for Math_ACT')" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_aux = df_total_new.copy()\n", "df_aux['Verbal_ACT'] = (df_aux['English_ACT'] + df_aux['Reading_ACT'])/2\n", "\n", "fig = plt.figure(figsize=(12,4))\n", "\n", "ax1 = fig.add_subplot(131)\n", "plt.boxplot(df_aux['Participation_ACT (%)'])\n", "ax1.set_title('Box plot for Participation_ACT (%)')\n", "\n", "ax2 = fig.add_subplot(132)\n", "plt.boxplot(df_aux['Verbal_ACT'])\n", "ax2.set_title('Box plot for Verbal_ACT')\n", "\n", "ax3 = fig.add_subplot(133)\n", "plt.boxplot(df_aux['Math_ACT'])\n", "ax3.set_title('Box plot for Math_ACT')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### BONUS: Using Tableau, create a heat map for each variable using a map of the US. " ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "##### To be done." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Step 4: Descriptive and Inferential Statistics" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 24. Summarize each distribution. As data scientists, be sure to back up these summaries with statistics. (Hint: What are the three things we care about when describing distributions?)\n", "\n", "We look into the mean, standard deviation and degree of skewness. The median and the $50\\%$ percentil values are the same by definition. " ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACT
mean76.142857529.666667517.90476234.66666722.83333322.83333323.70476222.800000
std16.95076919.65282021.58681318.5211592.1441391.6698301.7693151.553061
50%70.000000531.000000523.00000031.00000023.50000023.30000024.40000023.300000
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT Participation_ACT (%) \\\n", "mean 76.142857 529.666667 517.904762 34.666667 \n", "std 16.950769 19.652820 21.586813 18.521159 \n", "50% 70.000000 531.000000 523.000000 31.000000 \n", "\n", " English_ACT Math_ACT Reading_ACT Science_ACT \n", "mean 22.833333 22.833333 23.704762 22.800000 \n", "std 2.144139 1.669830 1.769315 1.553061 \n", "50% 23.500000 23.300000 24.400000 23.300000 " ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_aux[cols].describe().loc[['mean','std','50%']]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For example, magnitude of percentual differences between means and medians (values are in percentage so they are indeed low for the scores!):" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Participation_SAT (%) : 8.775510204081627\n", "EBRW_SAT : 0.25109855618330457\n", "Math_SAT : 0.9742329053992527\n", "Participation_ACT (%) : 11.827956989247301\n", "English_ACT : 2.8368794326241176\n", "Math_ACT : 2.002861230329045\n", "Reading_ACT : 2.849336455893814\n", "Science_ACT : 2.145922746781126\n", "Verbal_ACT : 2.8432249726612957\n" ] } ], "source": [ "for col in df_aux.columns.tolist():\n", " print (col,\":\",np.abs(100*(df_aux[col].describe().loc['mean']/df_aux[col].describe().loc['50%']-1)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 25. Summarize each relationship. Be sure to back up these summaries with statistics.\n", "\n", "**25.1) Let us look at correlations:**" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "cols_SAT = ['Participation_SAT (%)', 'EBRW_SAT', 'Math_SAT']\n", "cols_ACT = [ 'Participation_ACT (%)', 'Math_ACT', 'Science_ACT', 'Verbal_ACT']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**SAT**\n", "\n", "- For the SAT we see that the Math and EBRW scores are highly positively correlated\n", "- The participation rate and both scores have also a relatively strong negative correlation as discussed before." ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SAT
Participation_SAT (%)1.000000-0.656950-0.718164
EBRW_SAT-0.6569501.0000000.961519
Math_SAT-0.7181640.9615191.000000
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT\n", "Participation_SAT (%) 1.000000 -0.656950 -0.718164\n", "EBRW_SAT -0.656950 1.000000 0.961519\n", "Math_SAT -0.718164 0.961519 1.000000" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corr_SAT = df_aux[cols_SAT].corr()\n", "corr_SAT" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**ACT**\n", "\n", "- For the ACT we see that the Math, EBRW and Science scores are highly positively correlated as well\n", "- As in the SAT the participation rate and both scores have also a strong negative correlation but in the ACT it us slightly stronger" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_ACT (%)Math_ACTScience_ACTVerbal_ACT
Participation_ACT (%)1.000000-0.839660-0.854699-0.835211
Math_ACT-0.8396601.0000000.9879120.974774
Science_ACT-0.8546990.9879121.0000000.980839
Verbal_ACT-0.8352110.9747740.9808391.000000
\n", "
" ], "text/plain": [ " Participation_ACT (%) Math_ACT Science_ACT \\\n", "Participation_ACT (%) 1.000000 -0.839660 -0.854699 \n", "Math_ACT -0.839660 1.000000 0.987912 \n", "Science_ACT -0.854699 0.987912 1.000000 \n", "Verbal_ACT -0.835211 0.974774 0.980839 \n", "\n", " Verbal_ACT \n", "Participation_ACT (%) -0.835211 \n", "Math_ACT 0.974774 \n", "Science_ACT 0.980839 \n", "Verbal_ACT 1.000000 " ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "corr_ACT = df_aux[cols_ACT].corr()\n", "corr_ACT" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**25.2) Skewness general observations**\n", "\n", "The skewness is an important metric and is related to the mean and median. It can be measured using Pearson's coefficient, namely:\n", "\n", "$${g_1} = \\frac{{{\\mu _3}}}{{{\\sigma ^3}}}$$\n", "\n", "\n", "where the numerator is the third momentum. One way to relate the difference between mean and median to the skewness is to use (which is valid *for some particular distributions*):\n", "\n", "$$ g_1 = 2(\\mu-{\\rm{mode}})/\\sigma$$ \n", "\n", "or\n", "\n", "$$ \\mu-{\\rm{mode}} = (1/2) g_1 \\sigma$$\n", "\n", "Though this equality is not valid in general, *an estimation of skewness as an indirect measure of the difference between mode and median and vice-versa may be used heuristically.*\n", "\n", "**25.3) In our case**\n", "\n", "In our case, consider the Math scores for example. The median is larger so $g_1<0$. If the left tail is more pronounced than the right one the function has negative skewness. As we see below (where I reproduced the plots), the left tail is indeed more pronounced." ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "g1 from SAT Math is: -0.4837273105976173\n" ] } ], "source": [ "g1_SAT = 2*(np.mean(df_aux['Math_SAT'])-np.median(df_aux['Math_SAT']))/ np.std(df_aux['Math_SAT'])\n", "print (\"g1 from SAT Math is:\", g1_SAT)" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "g1 from ACT is: -0.5727420648104604\n" ] } ], "source": [ "g1_ACT = 2*(np.mean(df_aux['Math_ACT'])-np.median(df_aux['Math_ACT']))/ np.std(df_aux['Math_ACT'])\n", "print (\"g1 from ACT is:\", g1_ACT)" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 64, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 64, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "p1 = df_total_new[['Math_SAT']]\n", "p2 = df_total_new[['Math_ACT']]\n", "\n", "fig, axes = plt.subplots(1, 2,figsize=(6,2))\n", "\n", "p1.hist('Math_SAT', bins=10, ax=axes[0])\n", "p2.hist('Math_ACT', bins=10, ax=axes[1])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 26. Execute a hypothesis test comparing the SAT and ACT participation rates. Use $\\alpha = 0.05$. Be sure to interpret your results." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The full population of high-school graduates is divided into two groups namely, SAT test takers and ACT test takers. \n", "\n", "Suppose I want to test whether the true population mean of the participation rates are different between the SAT and ACT. Our hypotheses have the form: \n", "\n", "\n", "$${H_0}:\\,{\\mu _{{\\rm{PR,SAT}}}} = \\,{\\mu _{{\\rm{PR,ACT}}}}\\\\\n", "{H_{\\rm{A}}}:\\,{\\mu _{{\\rm{PR,SAT}}}} \\ne {\\mu _{{\\rm{PR,ACT}}}}$$\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To obtain the $p$-value we use:" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "('p-value is:', 3.0499821970067098e-09)" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"p-value is:\",stats.ttest_ind(df_aux['Participation_SAT (%)'],df_aux['Participation_ACT (%)'])[1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This is much smaller than $\\alpha$ so we reject the null hypothesis and conclude that both means differ at this level of confidence." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 27. Generate and interpret 95% confidence intervals for SAT and ACT participation rates.\n", "\n", "From below I conclude that I am 95$\\%$ confident that the true mean rate for the SAT participation is within (26.261598995475964, 43.071734337857364) and that the true mean rate for the ACT participation is within (68.450446510874016, 83.835267774840261)." ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [], "source": [ "#print df_aux['Participation_ACT (%)'].mean()\n", "#print df_aux['Participation_SAT (%)'].mean()" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Participation_SAT (%)EBRW_SATMath_SATParticipation_ACT (%)English_ACTMath_ACTReading_ACTScience_ACTVerbal_ACT
District of Columbia100.0482.0468.032.024.423.524.923.524.65
Michigan100.0509.0495.029.024.123.724.523.824.30
Connecticut100.0530.0512.031.025.524.625.624.625.55
Delaware100.0503.0492.018.024.123.424.823.624.45
New Hampshire96.0532.0520.018.025.425.126.024.925.70
\n", "
" ], "text/plain": [ " Participation_SAT (%) EBRW_SAT Math_SAT \\\n", "District of Columbia 100.0 482.0 468.0 \n", "Michigan 100.0 509.0 495.0 \n", "Connecticut 100.0 530.0 512.0 \n", "Delaware 100.0 503.0 492.0 \n", "New Hampshire 96.0 532.0 520.0 \n", "\n", " Participation_ACT (%) English_ACT Math_ACT \\\n", "District of Columbia 32.0 24.4 23.5 \n", "Michigan 29.0 24.1 23.7 \n", "Connecticut 31.0 25.5 24.6 \n", "Delaware 18.0 24.1 23.4 \n", "New Hampshire 18.0 25.4 25.1 \n", "\n", " Reading_ACT Science_ACT Verbal_ACT \n", "District of Columbia 24.9 23.5 24.65 \n", "Michigan 24.5 23.8 24.30 \n", "Connecticut 25.6 24.6 25.55 \n", "Delaware 24.8 23.6 24.45 \n", "New Hampshire 26.0 24.9 25.70 " ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_aux.head()" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(26.261598995475964, 43.071734337857364)" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "stats.t.interval(0.95,df_aux['Participation_ACT (%)'].shape[0],loc = df_aux['Participation_ACT (%)'].mean(),\n", " scale = (np.std(df_aux['Participation_ACT (%)'], ddof = 1)) / df_aux['Participation_ACT (%)'].shape[0] ** 0.5)" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(68.45044651087402, 83.83526777484026)" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "stats.t.interval(0.95,df_aux['Participation_SAT (%)'].shape[0],loc = df_aux['Participation_SAT (%)'].mean(),\n", " scale = (np.std(df_aux['Participation_SAT (%)'], ddof = 1)) / df_aux['Participation_SAT (%)'].shape[0] ** 0.5)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 28. Given your answer to 26, was your answer to 27 surprising? Why?" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "Not surprising since confidence that they differ must be associated with lack of overlap between confidence intervals.\n", "If we are confident that they are likely to belong to different intervals, it is intuitive that they should differ." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### 29. Is it appropriate to generate correlation between SAT and ACT math scores? Why?" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "Probably yes, since they have the same units and compare reasonably similar quantities (details about the test takers and some other factors for example may change that rationale)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##### Commentary about bin size\n", "- To choose the size of the bins one can use the Freedman–Diaconis rule which aims to minimize the difference between the area under the empirical and theoretical distributions ${\\rm{bin\\,\\, size}} = 2\\frac{{{\\rm{IQR}}(x)}}{{\\sqrt[3]{n}}}$ where $n$ is the number of observations in the sample and IQR is the difference between 75th and 25th percentiles. The package `astropy.visualization` contains this options and will be used in future projects." ] } ], "metadata": { "anaconda-cloud": {}, "kernelspec": { "display_name": "Python [conda env:anaconda3]", "language": "python", "name": "conda-env-anaconda3-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 1 }