{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Lesson 2 - Exploratory Data Analysis\n",
"\n",
"> A walkthrough on the fundamental mechanics to manipulate the data contained in pandas Series or DataFrame objects."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/lvwerra/dslectures/master?urlpath=lab/tree/notebooks%2Flesson02_exploratory-data-analysis.ipynb) [![slides](https://img.shields.io/static/v1?label=slides&message=2021-lesson02.pdf&color=blue&logo=Google-drive)](https://drive.google.com/file/d/1rLwnlpUCCQVU0hEFYM6cO4r_R48INMO2/view)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Learning objectives"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* Understand the main steps involved in exploratory data analysis\n",
"* Visualise geographical data with seaborn\n",
"* Slice, mask, and index `pandas.Series` and `pandas.DataFrame` objects\n",
"* Merge `pandas.DataFrame` objects together on a common key\n",
"* Apply the `DataFrame.groupby()` operation to aggregate data across different groups of interest"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## References"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This lesson draws heavily on the following textbook chapters:\n",
"\n",
"* Chapter 2 of _Hands-On Machine Learning with Scikit-Learn and TensorFlow_ by Aurèlien Geron\n",
"* Chapter 3 (pp. 146-170) of _Python Data Science Handbook_ by Jake Vanderplas\n",
"\n",
"You may also find the following blog post useful:\n",
"\n",
"* [Exploratory Data Analysis of Craft Beers: Data Profiling](https://www.datacamp.com/community/tutorials/python-data-profiling)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Homework\n",
"\n",
"* Solve the exercises included in this notebook\n",
"* Work through lesson 2 and 4 from [Kaggle Learn's](https://www.kaggle.com/learn/pandas) introduction to pandas\n",
"\n",
"If you get stuck on understanding a particular pandas technique, you might find their [docs](https://pandas.pydata.org/docs/) to be helpful."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## What is exploratory data analysis?"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"
\n",
"\n",
"
\n",
"\n",
"In data science we apply the scientific method to data with the goal gain insights. This means that we state a hypothesis about the data, test it and refine it if necessary. In this framework, exploratory data analysis (EDA) is the step where we explore the data before actually building models. This helps us understand what information is actually contained in the data and what insights could be gained from it. \n",
"\n",
"Formally, the goals of EDA are:\n",
"\n",
"- Suggest hypotheses about the phenomena of interest\n",
"- Check if necessary data is available to test these hypotheses\n",
"- Make a selection of appropriate methods and models to achieve the goal\n",
"- Suggest what data should be gathered for further investigation\n",
"\n",
"This exploratory phase lays out the path for the rest of a data science project and is therefore a crucial part of the process."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## The data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In this lesson we will analyse two datasets:\n",
"\n",
"* `housing.csv`\n",
"* `housing_addresses.csv`\n",
"\n",
"The first is the [California housing dataset](https://www.kaggle.com/camnugent/california-housing-prices) we saw in lesson 1, while the second provides information about the neighbourhoods associated with each house. This auxiliary data was generated using the [reverse geocoding](https://en.wikipedia.org/wiki/Reverse_geocoding) functionality from [Google Maps](https://developers.google.com/maps/documentation/geocoding/intro#ReverseGeocoding), where the latitude and longitude coordinates for each house are converted into the closest, human-readable address.\n",
"\n",
"The type of questions we will try to find answers to include:\n",
"\n",
"* Which cities have the most houses?\n",
"* Which cities have the most expensive houses?\n",
"* What is the breakdown of the house prices by proximity to the ocean?"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import libraries"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As in lesson 1, we will be making use of the pandas and seaborn libraries. It is often a good idea to import all your libraries in a single cell block near the top of your notebooks so that your collaborators can quickly see whether they need to install new libraries or not."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# reload modules before executing user code\n",
"%load_ext autoreload\n",
"# reload all modules every time before executing the Python code\n",
"%autoreload 2\n",
"# render plots in notebook\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# data wrangling\n",
"import pandas as pd\n",
"import numpy as np\n",
"from pathlib import Path\n",
"from dslectures.core import *\n",
"\n",
"# data viz\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"import matplotlib.image as mpimg\n",
"\n",
"# these commands define the color scheme\n",
"sns.set(color_codes=True)\n",
"sns.set_palette(sns.color_palette('muted'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load the data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As usual, we can download our datasets using our helper function `get_datasets`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Download of housing dataset complete.\n",
"Download of housing_addresses dataset complete.\n"
]
}
],
"source": [
"get_dataset('housing.csv')\n",
"get_dataset('housing_addresses.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We also make use of the `pathlib` library to handle our filepaths:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"housing (1).csv housing_gmaps_data_raw (1).csv\n",
"housing.csv housing_gmaps_data_raw.csv\n",
"housing_addresses (1).csv imdb.csv\n",
"housing_addresses.csv uc\n",
"housing_backup.csv\n"
]
}
],
"source": [
"DATA = Path('../data/')\n",
"!ls {DATA}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
"
],
"text/plain": [
" street_number route locality-political postal_code \\\n",
"0 3130 Grizzly Peak Boulevard Berkeley 94705.0 \n",
"1 2005 Tunnel Road Oakland 94611.0 \n",
"2 6886 Chabot Road Oakland 94618.0 \n",
"3 6365 Florio Street Oakland 94618.0 \n",
"4 5407 Bryant Avenue Oakland 94618.0 \n",
"\n",
" latitude_longitude \n",
"0 37.88,-122.23 \n",
"1 37.86,-122.22 \n",
"2 37.85,-122.24 \n",
"3 37.85,-122.25 \n",
"4 37.84,-122.25 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_addresses = pd.read_csv(DATA/'housing_addresses.csv'); housing_addresses.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Inspect the data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### The shape of data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Whenever we have a new dataset it is handy to begin by getting an idea of how large the `DataFrame` is. This can be done with either the `len` or `DataFrame.shape` methods:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(20640, 12590)"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get number of rows\n",
"len(housing_data), len(housing_addresses)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((20640, 10), (12590, 5))"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get tuples of (n_rows, n_columns)\n",
"housing_data.shape, housing_addresses.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Rename columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Usually one finds that the column headers in the raw data are either ambiguous or appear in multiple `DataFrame` objects, in which case it is handy to give them the same name. Although it's obvious from the `DataFrame.head()` method what the column headers are for our housing and address data, in most cases one has tens or hundreds of columns and the fastest way to see their names is as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['street_number', 'route', 'locality-political', 'postal_code',\n",
" 'latitude_longitude'],\n",
" dtype='object')"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_addresses.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's rename the `route` and `locality-political` columns to something more transparent:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"housing_addresses.rename(columns={'route':'street_name', 'locality-political':'city'}, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
street_number
\n",
"
street_name
\n",
"
city
\n",
"
postal_code
\n",
"
latitude_longitude
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
3130
\n",
"
Grizzly Peak Boulevard
\n",
"
Berkeley
\n",
"
94705.0
\n",
"
37.88,-122.23
\n",
"
\n",
"
\n",
"
1
\n",
"
2005
\n",
"
Tunnel Road
\n",
"
Oakland
\n",
"
94611.0
\n",
"
37.86,-122.22
\n",
"
\n",
"
\n",
"
2
\n",
"
6886
\n",
"
Chabot Road
\n",
"
Oakland
\n",
"
94618.0
\n",
"
37.85,-122.24
\n",
"
\n",
"
\n",
"
3
\n",
"
6365
\n",
"
Florio Street
\n",
"
Oakland
\n",
"
94618.0
\n",
"
37.85,-122.25
\n",
"
\n",
"
\n",
"
4
\n",
"
5407
\n",
"
Bryant Avenue
\n",
"
Oakland
\n",
"
94618.0
\n",
"
37.84,-122.25
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" street_number street_name city postal_code \\\n",
"0 3130 Grizzly Peak Boulevard Berkeley 94705.0 \n",
"1 2005 Tunnel Road Oakland 94611.0 \n",
"2 6886 Chabot Road Oakland 94618.0 \n",
"3 6365 Florio Street Oakland 94618.0 \n",
"4 5407 Bryant Avenue Oakland 94618.0 \n",
"\n",
" latitude_longitude \n",
"0 37.88,-122.23 \n",
"1 37.86,-122.22 \n",
"2 37.85,-122.24 \n",
"3 37.85,-122.25 \n",
"4 37.84,-122.25 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check that the renaming worked\n",
"housing_addresses.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Note: Many functions like `DataFrame.rename()` can manipulate an object _in-place_ without returning a new object. In other words, when `inplace=True` is passed the data is renamed in place as `data_frame.an_operation(inplace=True)` so we don't need the usual assignment `LHS = RHS`. By default, `inplace=False` so you have to set it explicitly if needed."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Unique values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Since we are dealing with data about California, we should check that the `city` column contains a reasonable number of unique entries. In pandas we can check this the `DataFrame.nunique()` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"989"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_addresses['city'].nunique()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"#### Exercise #1\n",
"\n",
"Does the above number make sense to you? What additional data could you find to determine if it does or does not?\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Visualising geographical data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In this lesson we will be focusing on how the house location affects its price, so let's make a scatterplot of the latitude and longitude values to see if we can identify any interesting patterns:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.scatterplot(x=\"longitude\", y=\"latitude\", data=housing_data);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Although the points look like the shape of California, we see that many are overlapping which obscures potentially interesting substructure. We can fix this by configuring the transparency of the points with the `alpha` argument:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.scatterplot(x=\"longitude\", y=\"latitude\", data=housing_data, alpha=0.1);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This is much better as we can now see distinct clusters of houses. To make this plot even more informative, let's colour the points according to the median house value; we will use the [viridis](https://bids.github.io/colormap/) colourmap (palette) as this has been carefully designed for data that has a sequential nature (i.e. low to high values):"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = sns.scatterplot(\n",
" x=\"longitude\",\n",
" y=\"latitude\",\n",
" data=housing_data,\n",
" alpha=0.1,\n",
" hue=\"median_house_value\",\n",
" palette=\"viridis\",\n",
" size=housing_data[\"population\"] / 100\n",
")\n",
"\n",
"# place legend outside of figure\n",
"fig.legend(loc=\"center left\", bbox_to_anchor=(1.01, 0.6), ncol=1);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"#### Exercise #2\n",
"\n",
"What does the figure above tell us about the relationship between house prices and location or population density? \n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally, to make our visualisation a little more intuitive, we can also overlay the scatter plot on an actual map of California:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = sns.scatterplot(\n",
" x=\"longitude\",\n",
" y=\"latitude\",\n",
" data=housing_data,\n",
" alpha=0.1,\n",
" hue=\"median_house_value\",\n",
" palette=\"viridis\",\n",
" size=housing_data[\"population\"] / 100\n",
")\n",
"\n",
"# place legend outside of figure\n",
"fig.legend(loc=\"center left\", bbox_to_anchor=(1.01, 0.6), ncol=1);\n",
"\n",
"# ref - www.kaggle.com/camnugent/geospatial-feature-engineering-and-visualization/\n",
"california_img=mpimg.imread('images/california.png')\n",
"plt.imshow(california_img, extent=[-124.55, -113.80, 32.45, 42.05], alpha=0.5);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"#### Exercise #3\n",
"\n",
"Can you explain the light green and yellow hotspots in the above figure?\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Merging DataFrames"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Although the `housing_data` and `housing_addresses` `DataFrames` contain interesting information, it would be nice if there was a way to join the two tables.\n",
"\n",
"More generally, one of the most common operations in pandas (or data science for that matter) is the combination of data contained in various objects. In particular, _**merge**_ or _**join**_ operations combine datasets by linking rows using one of more _**keys**_. These operations are central to relational databases (e.g. SQL-based). The `pandas.merge()` function in pandas is the main entry point for using these algorithms on your data. \n",
"\n",
"Let's use this idea to combine the `housing_data` and `housing_addresses` `pandas.DataFrame` objects via their common latitude and longitude coordinates. First we need to combine the `latitude` and `longitude` columns of `housing_data` into the same `lat,lon` format as our `housing_addresses` `pandas.DataFrame`. To do so, we will use the `Series.astype()` function to convert the numerical column values to strings, then use string concatenation to create a new `latitude_longitude` column with the desired format:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
longitude
\n",
"
latitude
\n",
"
housing_median_age
\n",
"
total_rooms
\n",
"
total_bedrooms
\n",
"
population
\n",
"
households
\n",
"
median_income
\n",
"
median_house_value
\n",
"
ocean_proximity
\n",
"
latitude_longitude
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
-122.23
\n",
"
37.88
\n",
"
41.0
\n",
"
880.0
\n",
"
129.0
\n",
"
322.0
\n",
"
126.0
\n",
"
8.3252
\n",
"
452600.0
\n",
"
NEAR BAY
\n",
"
37.88,-122.23
\n",
"
\n",
"
\n",
"
1
\n",
"
-122.22
\n",
"
37.86
\n",
"
21.0
\n",
"
7099.0
\n",
"
1106.0
\n",
"
2401.0
\n",
"
1138.0
\n",
"
8.3014
\n",
"
358500.0
\n",
"
NEAR BAY
\n",
"
37.86,-122.22
\n",
"
\n",
"
\n",
"
2
\n",
"
-122.24
\n",
"
37.85
\n",
"
52.0
\n",
"
1467.0
\n",
"
190.0
\n",
"
496.0
\n",
"
177.0
\n",
"
7.2574
\n",
"
352100.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.24
\n",
"
\n",
"
\n",
"
3
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1274.0
\n",
"
235.0
\n",
"
558.0
\n",
"
219.0
\n",
"
5.6431
\n",
"
341300.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.25
\n",
"
\n",
"
\n",
"
4
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1627.0
\n",
"
280.0
\n",
"
565.0
\n",
"
259.0
\n",
"
3.8462
\n",
"
342200.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.25
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
"0 -122.23 37.88 41.0 880.0 129.0 \n",
"1 -122.22 37.86 21.0 7099.0 1106.0 \n",
"2 -122.24 37.85 52.0 1467.0 190.0 \n",
"3 -122.25 37.85 52.0 1274.0 235.0 \n",
"4 -122.25 37.85 52.0 1627.0 280.0 \n",
"\n",
" population households median_income median_house_value ocean_proximity \\\n",
"0 322.0 126.0 8.3252 452600.0 NEAR BAY \n",
"1 2401.0 1138.0 8.3014 358500.0 NEAR BAY \n",
"2 496.0 177.0 7.2574 352100.0 NEAR BAY \n",
"3 558.0 219.0 5.6431 341300.0 NEAR BAY \n",
"4 565.0 259.0 3.8462 342200.0 NEAR BAY \n",
"\n",
" latitude_longitude \n",
"0 37.88,-122.23 \n",
"1 37.86,-122.22 \n",
"2 37.85,-122.24 \n",
"3 37.85,-122.25 \n",
"4 37.85,-122.25 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# create new column\n",
"housing_data['latitude_longitude'] = housing_data['latitude'].astype(str) + ',' + housing_data['longitude'].astype(str)\n",
"# check the column was created\n",
"housing_data.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"--- \n",
"\n",
"#### Exercise #4\n",
"\n",
"Calculate the number of unique values in the `latitude_longitude` column of both `housing_data` and `housing_addresses`.\n",
"\n",
"* What can you conclude from this comparison? \n",
"* Why do you think there might be less unique coordinate pairs than the total number of houses?\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that we have `latitude_longitude` present in both `pandas.DataFrame` objects we can merge the two tables together in pandas as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
longitude
\n",
"
latitude
\n",
"
housing_median_age
\n",
"
total_rooms
\n",
"
total_bedrooms
\n",
"
population
\n",
"
households
\n",
"
median_income
\n",
"
median_house_value
\n",
"
ocean_proximity
\n",
"
latitude_longitude
\n",
"
street_number
\n",
"
street_name
\n",
"
city
\n",
"
postal_code
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
-122.23
\n",
"
37.88
\n",
"
41.0
\n",
"
880.0
\n",
"
129.0
\n",
"
322.0
\n",
"
126.0
\n",
"
8.3252
\n",
"
452600.0
\n",
"
NEAR BAY
\n",
"
37.88,-122.23
\n",
"
3130
\n",
"
Grizzly Peak Boulevard
\n",
"
Berkeley
\n",
"
94705.0
\n",
"
\n",
"
\n",
"
1
\n",
"
-122.22
\n",
"
37.86
\n",
"
21.0
\n",
"
7099.0
\n",
"
1106.0
\n",
"
2401.0
\n",
"
1138.0
\n",
"
8.3014
\n",
"
358500.0
\n",
"
NEAR BAY
\n",
"
37.86,-122.22
\n",
"
2005
\n",
"
Tunnel Road
\n",
"
Oakland
\n",
"
94611.0
\n",
"
\n",
"
\n",
"
2
\n",
"
-122.24
\n",
"
37.85
\n",
"
52.0
\n",
"
1467.0
\n",
"
190.0
\n",
"
496.0
\n",
"
177.0
\n",
"
7.2574
\n",
"
352100.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.24
\n",
"
6886
\n",
"
Chabot Road
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
"
\n",
"
3
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1274.0
\n",
"
235.0
\n",
"
558.0
\n",
"
219.0
\n",
"
5.6431
\n",
"
341300.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.25
\n",
"
6365
\n",
"
Florio Street
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
"
\n",
"
4
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1627.0
\n",
"
280.0
\n",
"
565.0
\n",
"
259.0
\n",
"
3.8462
\n",
"
342200.0
\n",
"
NEAR BAY
\n",
"
37.85,-122.25
\n",
"
6365
\n",
"
Florio Street
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
"0 -122.23 37.88 41.0 880.0 129.0 \n",
"1 -122.22 37.86 21.0 7099.0 1106.0 \n",
"2 -122.24 37.85 52.0 1467.0 190.0 \n",
"3 -122.25 37.85 52.0 1274.0 235.0 \n",
"4 -122.25 37.85 52.0 1627.0 280.0 \n",
"\n",
" population households median_income median_house_value ocean_proximity \\\n",
"0 322.0 126.0 8.3252 452600.0 NEAR BAY \n",
"1 2401.0 1138.0 8.3014 358500.0 NEAR BAY \n",
"2 496.0 177.0 7.2574 352100.0 NEAR BAY \n",
"3 558.0 219.0 5.6431 341300.0 NEAR BAY \n",
"4 565.0 259.0 3.8462 342200.0 NEAR BAY \n",
"\n",
" latitude_longitude street_number street_name city \\\n",
"0 37.88,-122.23 3130 Grizzly Peak Boulevard Berkeley \n",
"1 37.86,-122.22 2005 Tunnel Road Oakland \n",
"2 37.85,-122.24 6886 Chabot Road Oakland \n",
"3 37.85,-122.25 6365 Florio Street Oakland \n",
"4 37.85,-122.25 6365 Florio Street Oakland \n",
"\n",
" postal_code \n",
"0 94705.0 \n",
"1 94611.0 \n",
"2 94618.0 \n",
"3 94618.0 \n",
"4 94618.0 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# create a new DataFrame from the merge\n",
"housing_merged = pd.merge(\n",
" housing_data, housing_addresses, how=\"left\", on=\"latitude_longitude\"\n",
")\n",
"# check merge worked\n",
"housing_merged.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Boom! We now have a single `pandas.DataFrame` that links information for house prices and attributes and their addresses."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Note: The merge operation above is an example of a _left join_, namely we use all the key combinations of `latitude_longitude` found in the left table `housing_data`. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In general the `'how'` argument of `pandas.merge()` allows four different join types:\n",
"* `'left'`: Use all key combinations found in the left table\n",
"* `'right'`: Use all key combinations found in the right table\n",
"* `'inner'`: Use only the key combinations observed in both tables\n",
"* `'outer'`: Use all key combinations observed in both tables together\n",
"\n",
"A visual example of these different merges in action is shown in the figure below."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
" \n",
"\n",
"
Figure: Graphical representation of the different types of merges between two DataFrames df1 and df2 that are possible in pandas.
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Warning: If the keys in one table match more than one row in the other `pandas.DataFrame` you can expect a _larger_ table to appear after you do a left join. To avoid this behaviour, you can run `DataFrame.drop_duplicates()` before doing the merge."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Dropping columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"It is not uncommon for a dataset to have tens or hundreds of columns, and in practice we may only want to focus our attention on a smaller subset. One way to remove unwanted columns is via the `DataFrame.drop()` method. Since we have duplicate information about the latitude and longitude coordinate, we may as well drop the `latitude_longitude` column from our merged `pandas.DataFrame`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
longitude
\n",
"
latitude
\n",
"
housing_median_age
\n",
"
total_rooms
\n",
"
total_bedrooms
\n",
"
population
\n",
"
households
\n",
"
median_income
\n",
"
median_house_value
\n",
"
ocean_proximity
\n",
"
street_number
\n",
"
street_name
\n",
"
city
\n",
"
postal_code
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
-122.23
\n",
"
37.88
\n",
"
41.0
\n",
"
880.0
\n",
"
129.0
\n",
"
322.0
\n",
"
126.0
\n",
"
8.3252
\n",
"
452600.0
\n",
"
NEAR BAY
\n",
"
3130
\n",
"
Grizzly Peak Boulevard
\n",
"
Berkeley
\n",
"
94705.0
\n",
"
\n",
"
\n",
"
1
\n",
"
-122.22
\n",
"
37.86
\n",
"
21.0
\n",
"
7099.0
\n",
"
1106.0
\n",
"
2401.0
\n",
"
1138.0
\n",
"
8.3014
\n",
"
358500.0
\n",
"
NEAR BAY
\n",
"
2005
\n",
"
Tunnel Road
\n",
"
Oakland
\n",
"
94611.0
\n",
"
\n",
"
\n",
"
2
\n",
"
-122.24
\n",
"
37.85
\n",
"
52.0
\n",
"
1467.0
\n",
"
190.0
\n",
"
496.0
\n",
"
177.0
\n",
"
7.2574
\n",
"
352100.0
\n",
"
NEAR BAY
\n",
"
6886
\n",
"
Chabot Road
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
"
\n",
"
3
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1274.0
\n",
"
235.0
\n",
"
558.0
\n",
"
219.0
\n",
"
5.6431
\n",
"
341300.0
\n",
"
NEAR BAY
\n",
"
6365
\n",
"
Florio Street
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
"
\n",
"
4
\n",
"
-122.25
\n",
"
37.85
\n",
"
52.0
\n",
"
1627.0
\n",
"
280.0
\n",
"
565.0
\n",
"
259.0
\n",
"
3.8462
\n",
"
342200.0
\n",
"
NEAR BAY
\n",
"
6365
\n",
"
Florio Street
\n",
"
Oakland
\n",
"
94618.0
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
"0 -122.23 37.88 41.0 880.0 129.0 \n",
"1 -122.22 37.86 21.0 7099.0 1106.0 \n",
"2 -122.24 37.85 52.0 1467.0 190.0 \n",
"3 -122.25 37.85 52.0 1274.0 235.0 \n",
"4 -122.25 37.85 52.0 1627.0 280.0 \n",
"\n",
" population households median_income median_house_value ocean_proximity \\\n",
"0 322.0 126.0 8.3252 452600.0 NEAR BAY \n",
"1 2401.0 1138.0 8.3014 358500.0 NEAR BAY \n",
"2 496.0 177.0 7.2574 352100.0 NEAR BAY \n",
"3 558.0 219.0 5.6431 341300.0 NEAR BAY \n",
"4 565.0 259.0 3.8462 342200.0 NEAR BAY \n",
"\n",
" street_number street_name city postal_code \n",
"0 3130 Grizzly Peak Boulevard Berkeley 94705.0 \n",
"1 2005 Tunnel Road Oakland 94611.0 \n",
"2 6886 Chabot Road Oakland 94618.0 \n",
"3 6365 Florio Street Oakland 94618.0 \n",
"4 6365 Florio Street Oakland 94618.0 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# inplace=True manipulates an object without returning a new object\n",
"housing_merged.drop(['latitude_longitude'], axis=1, inplace=True); housing_merged.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Note: You will often encounter the cryptic axis parameter when dealing with `pandas.DataFrame` and `pandas.Series` objects. This parameter is used to specify along which dimension we want to apply a given transformation - see the figure below for a graphical representation."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
" \n",
"\n",
"
Figure: Visualisation of the axis parameter in pandas.
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Saving a DataFrame to disk"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"At this point, we have a unfified table with housing data and their addresses. This is usually a good point to save the intermediate results to disk so that we can reload them without having to run all preprocessing steps. To do so in pandas, we can make use of the `DataFrame.to_csv()` function:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# use index=False to avoid adding an extra column for the index\n",
"housing_merged.to_csv(path_or_buf=DATA/'housing_merged.csv', index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Indexing, selection, and filtering"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now that we have a tidy `pandas.DataFrame` let's apply some of the most common pandas methods to make queries on the data."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Series"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A `pandas.Series` object provides array-style item selection that allows one to perform _slicing, masking,_ and _fancy indexing_. For example, we can study the `housing_median_age` colum from a variety of angles:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# define a new Series object \n",
"age = housing_merged['housing_median_age']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 41.0\n",
"1 21.0\n",
"2 52.0\n",
"3 52.0\n",
"4 52.0\n",
" ... \n",
"20635 25.0\n",
"20636 18.0\n",
"20637 17.0\n",
"20638 18.0\n",
"20639 16.0\n",
"Name: housing_median_age, Length: 20640, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"41.0"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get first entry\n",
"age[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2 52.0\n",
"3 52.0\n",
"4 52.0\n",
"Name: housing_median_age, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# slicing by index\n",
"age[2:5]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([52., 52., 52.])"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# slice and just get values\n",
"age[2:5].values"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 20640.000000\n",
"mean 28.639486\n",
"std 12.585558\n",
"min 1.000000\n",
"25% 18.000000\n",
"50% 29.000000\n",
"75% 37.000000\n",
"max 52.000000\n",
"Name: housing_median_age, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"75 17.0\n",
"77 19.0\n",
"80 17.0\n",
"90 16.0\n",
"131 18.0\n",
" ... \n",
"20632 15.0\n",
"20636 18.0\n",
"20637 17.0\n",
"20638 18.0\n",
"20639 16.0\n",
"Name: housing_median_age, Length: 4259, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# masking (filtering)\n",
"age[(age > 10.0) & (age < 20.0)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 41.0\n",
"4 52.0\n",
"Name: housing_median_age, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# fancy indexing\n",
"age[[0, 4]]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### DataFrame"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Since a `pandas.DataFrame` acts like a two-dimensional array, pandas provides special indexing operators called `DataFrame.iloc[]` and `DataFrame.loc[]` to slice and dice our data. As an example, let's select a single row and multiple columns by _**label**_:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"city Oakland\n",
"population 496\n",
"Name: 2, dtype: object"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged.loc[2, ['city', 'population']]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can perform similar selections with _**integers**_ using `DataFrame.iloc[]`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"total_rooms 1467\n",
"street_name Chabot Road\n",
"Name: 2, dtype: object"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged.iloc[2, [3, 11]]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Masks or filters are especially common to use, e.g. let's select the subset of expensive houses:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
"
],
"text/plain": [
" longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
"701 -121.97 37.64 32.0 1283.0 194.0 \n",
"830 -121.99 37.61 9.0 3666.0 711.0 \n",
"859 -121.97 37.57 21.0 4342.0 783.0 \n",
"860 -121.96 37.58 15.0 3575.0 597.0 \n",
"861 -121.98 37.58 20.0 4126.0 1031.0 \n",
"... ... ... ... ... ... \n",
"20502 -118.68 34.33 45.0 121.0 25.0 \n",
"20503 -118.75 34.33 27.0 534.0 85.0 \n",
"20504 -118.73 34.29 11.0 5451.0 736.0 \n",
"20505 -118.72 34.29 22.0 3266.0 529.0 \n",
"20506 -118.73 34.29 8.0 4983.0 754.0 \n",
"\n",
" population households median_income median_house_value \\\n",
"701 485.0 171.0 6.0574 431000.0 \n",
"830 2341.0 703.0 4.6458 217000.0 \n",
"859 2172.0 789.0 4.6146 247600.0 \n",
"860 1777.0 559.0 5.7192 283500.0 \n",
"861 2079.0 975.0 3.6832 216900.0 \n",
"... ... ... ... ... \n",
"20502 67.0 27.0 2.9821 325000.0 \n",
"20503 243.0 77.0 8.2787 330000.0 \n",
"20504 2526.0 752.0 7.3550 343900.0 \n",
"20505 1595.0 494.0 6.0368 248000.0 \n",
"20506 2510.0 725.0 6.9454 276500.0 \n",
"\n",
" ocean_proximity street_number street_name city \\\n",
"701 <1H OCEAN 33803 Palomares Road Castro Valley \n",
"830 <1H OCEAN NaN South Fork Trail Castro Valley \n",
"859 <1H OCEAN 121 Overacker Terrace Fremont \n",
"860 <1H OCEAN NaN Deer Gulch Loop Trail Fremont \n",
"861 <1H OCEAN 37296 Mission Boulevard Fremont \n",
"... ... ... ... ... \n",
"20502 <1H OCEAN NaN Windmill Canyon Road Simi Valley \n",
"20503 <1H OCEAN NaN Middle Ridge Fire Road Simi Valley \n",
"20504 <1H OCEAN 3435 Avenida Simi Simi Valley \n",
"20505 <1H OCEAN 3889 Avenida Simi Simi Valley \n",
"20506 <1H OCEAN 3435 Avenida Simi Simi Valley \n",
"\n",
" postal_code \n",
"701 94552.0 \n",
"830 94552.0 \n",
"859 94536.0 \n",
"860 94536.0 \n",
"861 94536.0 \n",
"... ... \n",
"20502 93063.0 \n",
"20503 93065.0 \n",
"20504 93063.0 \n",
"20505 93063.0 \n",
"20506 93063.0 \n",
"\n",
"[11794 rows x 14 columns]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged.loc[housing_merged['ocean_proximity'].str.contains('O')]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Note: An important feature with `pandas.Series` and `pandas.DataFrame` objects is the fact that they contain an _**index**_ that lets us slice and modify the data. This `Index` object can be accessed via `Series.index` or `DataFrame.index` and is typically an array of integers that denote the location of each row."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For example, our `age` object has an index for each row or house in the dataset:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([ 0, 1, 2, 3, 4, 5, 6, 7, 8,\n",
" 9,\n",
" ...\n",
" 20630, 20631, 20632, 20633, 20634, 20635, 20636, 20637, 20638,\n",
" 20639],\n",
" dtype='int64', length=20640)"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.index"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can also sort the values according to the index, which in our example amounts to reversing the order:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"20639 16.0\n",
"20638 18.0\n",
"20637 17.0\n",
"20636 18.0\n",
"20635 25.0\n",
" ... \n",
"4 52.0\n",
"3 52.0\n",
"2 52.0\n",
"1 21.0\n",
"0 41.0\n",
"Name: housing_median_age, Length: 20640, dtype: float64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.sort_index(ascending=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally, there are times when you want to reset the index of the `pandas.Series` or `pandas.DataFrame` objects; this can be achieved as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
index
\n",
"
housing_median_age
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
0
\n",
"
41.0
\n",
"
\n",
"
\n",
"
1
\n",
"
1
\n",
"
21.0
\n",
"
\n",
"
\n",
"
2
\n",
"
2
\n",
"
52.0
\n",
"
\n",
"
\n",
"
3
\n",
"
3
\n",
"
52.0
\n",
"
\n",
"
\n",
"
4
\n",
"
4
\n",
"
52.0
\n",
"
\n",
"
\n",
"
...
\n",
"
...
\n",
"
...
\n",
"
\n",
"
\n",
"
20635
\n",
"
20635
\n",
"
25.0
\n",
"
\n",
"
\n",
"
20636
\n",
"
20636
\n",
"
18.0
\n",
"
\n",
"
\n",
"
20637
\n",
"
20637
\n",
"
17.0
\n",
"
\n",
"
\n",
"
20638
\n",
"
20638
\n",
"
18.0
\n",
"
\n",
"
\n",
"
20639
\n",
"
20639
\n",
"
16.0
\n",
"
\n",
" \n",
"
\n",
"
20640 rows × 2 columns
\n",
"
"
],
"text/plain": [
" index housing_median_age\n",
"0 0 41.0\n",
"1 1 21.0\n",
"2 2 52.0\n",
"3 3 52.0\n",
"4 4 52.0\n",
"... ... ...\n",
"20635 20635 25.0\n",
"20636 20636 18.0\n",
"20637 20637 17.0\n",
"20638 20638 18.0\n",
"20639 20639 16.0\n",
"\n",
"[20640 rows x 2 columns]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.reset_index()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note this creates a new `index` column and resets the order of the `pandas.Series` object in ascending order.\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Which cities have the most houses?"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Whenever you need to quickly find the frequencies associated with categorical data, the `DataFrame.value_counts()` and `Series.nlargest()` functions come in handy. For example, if we want to see which city has the most houses, we can run the following:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Los Angeles 2372\n",
"San Diego 809\n",
"San Francisco 574\n",
"San Jose 498\n",
"Sacramento 422\n",
"Oakland 374\n",
"Long Beach 317\n",
"Fresno 309\n",
"Stockton 242\n",
"Bakersfield 222\n",
"Name: city, dtype: int64"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged['city'].value_counts().nlargest(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This seems to make sense, since Los Angeles, San Diego, and San Francisco have some of the largest populations. We can check whether this is indeed the case by *aggregating* the data to calculate the *total* population value across the *group* of cities. pandas provides a flexibly `DataFrame.groupby()` interface that enables us to slice, dice, and summarise datasets in a natural way. In particular, pandas allows one to:\n",
"\n",
"* Split a pandas object into pieces using one or more keys\n",
"* Calculate group summary statistics, like count, mean, standard deviation, or a user-defined function\n",
"* Apply within-group transformations or other manipulations, like normalisation, rank, or subset selection\n",
"* Compute pivot tables and cross-tabulations.\n",
"\n",
"Let's combine these ideas to answer our question, followed by an explanation of how the GroupBy mechanics really work:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
population
\n",
"
\n",
"
\n",
"
city
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"
Acampo
\n",
"
9626.0
\n",
"
\n",
"
\n",
"
Acton
\n",
"
6740.0
\n",
"
\n",
"
\n",
"
Adelanto
\n",
"
6583.0
\n",
"
\n",
"
\n",
"
Adin
\n",
"
364.0
\n",
"
\n",
"
\n",
"
Agoura Hills
\n",
"
26776.0
\n",
"
\n",
"
\n",
"
...
\n",
"
...
\n",
"
\n",
"
\n",
"
Yreka
\n",
"
8971.0
\n",
"
\n",
"
\n",
"
Yuba City
\n",
"
49772.0
\n",
"
\n",
"
\n",
"
Yucaipa
\n",
"
31965.0
\n",
"
\n",
"
\n",
"
Yucca Valley
\n",
"
18955.0
\n",
"
\n",
"
\n",
"
Zenia
\n",
"
228.0
\n",
"
\n",
" \n",
"
\n",
"
989 rows × 1 columns
\n",
"
"
],
"text/plain": [
" population\n",
"city \n",
"Acampo 9626.0\n",
"Acton 6740.0\n",
"Adelanto 6583.0\n",
"Adin 364.0\n",
"Agoura Hills 26776.0\n",
"... ...\n",
"Yreka 8971.0\n",
"Yuba City 49772.0\n",
"Yucaipa 31965.0\n",
"Yucca Valley 18955.0\n",
"Zenia 228.0\n",
"\n",
"[989 rows x 1 columns]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged.groupby('city').agg({'population':'sum'})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This seems to work - we now have the average number of people residing in a block of houses, but the result seems to be sorted alphabetically. To get the cities with the largest populations, we can use the `Series.sort_values()` method as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
population
\n",
"
\n",
"
\n",
"
city
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"
Los Angeles
\n",
"
3495957.0
\n",
"
\n",
"
\n",
"
San Diego
\n",
"
1069557.0
\n",
"
\n",
"
\n",
"
San Jose
\n",
"
818234.0
\n",
"
\n",
"
\n",
"
San Francisco
\n",
"
702282.0
\n",
"
\n",
"
\n",
"
Sacramento
\n",
"
614478.0
\n",
"
\n",
"
\n",
"
...
\n",
"
...
\n",
"
\n",
"
\n",
"
Parker
\n",
"
83.0
\n",
"
\n",
"
\n",
"
El Portal
\n",
"
79.0
\n",
"
\n",
"
\n",
"
Pearsonville
\n",
"
48.0
\n",
"
\n",
"
\n",
"
Forest Ranch
\n",
"
47.0
\n",
"
\n",
"
\n",
"
North Richmond
\n",
"
42.0
\n",
"
\n",
" \n",
"
\n",
"
989 rows × 1 columns
\n",
"
"
],
"text/plain": [
" population\n",
"city \n",
"Los Angeles 3495957.0\n",
"San Diego 1069557.0\n",
"San Jose 818234.0\n",
"San Francisco 702282.0\n",
"Sacramento 614478.0\n",
"... ...\n",
"Parker 83.0\n",
"El Portal 79.0\n",
"Pearsonville 48.0\n",
"Forest Ranch 47.0\n",
"North Richmond 42.0\n",
"\n",
"[989 rows x 1 columns]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing_merged.groupby(\"city\").agg({\"population\": \"sum\"}).sort_values(\n",
" by=\"population\", ascending=False\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"That's much better! We can store the result as a new `pandas.DataFrame` and plot the distribution:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# use outer parentheses () to add line breaks\n",
"top10_largest_cities = (\n",
" # group by key=city\n",
" housing_merged.groupby(\"city\")\n",
" # calculate total population\n",
" .agg({\"population\": \"sum\"})\n",
" # select 10 largest\n",
" .nlargest(10, columns=\"population\")\n",
" # reset index so city becomes column\n",
" .reset_index()\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
city
\n",
"
population
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
Los Angeles
\n",
"
3495957.0
\n",
"
\n",
"
\n",
"
1
\n",
"
San Diego
\n",
"
1069557.0
\n",
"
\n",
"
\n",
"
2
\n",
"
San Jose
\n",
"
818234.0
\n",
"
\n",
"
\n",
"
3
\n",
"
San Francisco
\n",
"
702282.0
\n",
"
\n",
"
\n",
"
4
\n",
"
Sacramento
\n",
"
614478.0
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" city population\n",
"0 Los Angeles 3495957.0\n",
"1 San Diego 1069557.0\n",
"2 San Jose 818234.0\n",
"3 San Francisco 702282.0\n",
"4 Sacramento 614478.0"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"top10_largest_cities.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.barplot(x='population', y='city', data=top10_largest_cities, color='b');"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## GroupBy mechanics"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The group operation above can be best understood by the H. Wickam's [_split-apply-combine_](https://medium.com/analytics-vidhya/split-apply-combine-strategy-for-data-mining-4fd6e2a0cc99) strategy, where you break up a big problem into manageable pieces, operate on each piece independently and then put all the pieces back together. \n",
"\n",
"**Split:**\n",
"In the first stage of the process, data contained in a `pandas.Series` or `pandas.DataFrame` object is _split_ into groups based on one or more specified _keys_. The splitting is performed on a particular _axis_ of the object (see the notebook from lesson 2). For example, a `pandas.DataFrame` can be grouped on its rows (`axis=0`) or its columns (`axis=1`).\n",
"\n",
"**Apply:**\n",
"Once the split done, a function is _applied_ to each group, producing a new value. \n",
"\n",
"**Combine:**\n",
"Finally, the results of all those function applications are _combined_ into a result object. The form of the resulting object will usualy depend on the what's being done to the data.\n",
"\n",
"See the figure below for an example of a simple group aggregation.\n",
"\n",
" \n",
"\n",
"
Figure: Illustraion of a group aggregation.
\n",
"\n",
"In general, the grouping key can take many forms and the key do not have to be all of the same type. Frequently, the grouping information is found in the same `pandas.DataFrame` as the data you want to work on, so the key is usually a _column name_. For example let's create a simple `pandas.DataFrame` as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
key1
\n",
"
key2
\n",
"
data1
\n",
"
data2
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
a
\n",
"
one
\n",
"
1.837510
\n",
"
0.875095
\n",
"
\n",
"
\n",
"
1
\n",
"
a
\n",
"
two
\n",
"
0.771915
\n",
"
-0.256958
\n",
"
\n",
"
\n",
"
2
\n",
"
b
\n",
"
one
\n",
"
-0.830038
\n",
"
-0.037795
\n",
"
\n",
"
\n",
"
3
\n",
"
b
\n",
"
two
\n",
"
0.727881
\n",
"
-0.254475
\n",
"
\n",
"
\n",
"
4
\n",
"
a
\n",
"
one
\n",
"
0.168928
\n",
"
-1.287844
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" key1 key2 data1 data2\n",
"0 a one 1.837510 0.875095\n",
"1 a two 0.771915 -0.256958\n",
"2 b one -0.830038 -0.037795\n",
"3 b two 0.727881 -0.254475\n",
"4 a one 0.168928 -1.287844"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_foo = pd.DataFrame(\n",
" {\n",
" \"key1\": [\"a\", \"a\", \"b\", \"b\", \"a\"],\n",
" \"key2\": [\"one\", \"two\", \"one\", \"two\", \"one\"],\n",
" \"data1\": np.random.randn(5),\n",
" \"data2\": np.random.randn(5),\n",
" }\n",
")\n",
"df_foo"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can then use the column names as the group keys (similar to what we did above with the beers):"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"grouped = df_foo.groupby('key1'); grouped"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This `grouped` variable is now a _GroupBy_ object. It has not actually calculated anything yet except for some intermediate data about the group key `df_foo['key1']`. The main idea is that this object has all of the information needed to then apply some operation to each of the groups. For example, we can get the mean per group as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
data1
\n",
"
data2
\n",
"
\n",
"
\n",
"
key1
\n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"
a
\n",
"
0.926117
\n",
"
-0.223236
\n",
"
\n",
"
\n",
"
b
\n",
"
-0.051078
\n",
"
-0.146135
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" data1 data2\n",
"key1 \n",
"a 0.926117 -0.223236\n",
"b -0.051078 -0.146135"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_grouped = grouped.mean(); df_grouped"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"#### Exercise #5\n",
"\n",
"* Use the above `DataFrame.groupby()` techniques to find the top 10 cities which have the most expensive houses on average. Look up some of the names on the web - do the results make sense?\n",
"* Use the `DataFrame.loc[]` method to filter out the houses with the capped values of over $500,000. Repeat the same step as above. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Exercise #6\n",
"\n",
"* Use the `DataFrame.groupby()` and `agg()` techniques to find the distribution of mean house prices according to `ocean_proximity`.\n",
"* Store the result from the above step in a new `pandas.DataFrame` and visualise it with seaborn's barplot.\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}