{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1.0\n",
"1.14.2\n"
]
}
],
"source": [
"import os\n",
"import numpy as np\n",
"import csv\n",
"\n",
"print csv.__version__\n",
"print np.__version__"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"# open file\n",
"# set delimiter as ';'\n",
"# typecast to list and store to variable \"wine\"\n",
"\n",
"DATA_DIR = '../data'\n",
"\n",
"with open(os.path.abspath(os.path.join(DATA_DIR, 'day7/winequality-white.csv')), 'r') as datafile:\n",
" reader = csv.reader(datafile, delimiter=\";\")\n",
" wines = list(reader)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['fixed acidity',\n",
" 'volatile acidity',\n",
" 'citric acid',\n",
" 'residual sugar',\n",
" 'chlorides',\n",
" 'free sulfur dioxide',\n",
" 'total sulfur dioxide',\n",
" 'density',\n",
" 'pH',\n",
" 'sulphates',\n",
" 'alcohol',\n",
" 'quality']"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wines[0]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total records: 4898\n"
]
}
],
"source": [
"# -1 to avoid header from counting into records\n",
"print 'Total records: {}'.format(len(wines)-1)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5.87790935076\n"
]
}
],
"source": [
"# average of quality variable\n",
"qualities = [float(item[-1]) for item in wines[1:]]\n",
"print sum(qualities)/len(qualities)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(4898, 12)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# converting python array to numpy array and typecasting the cell values to float\n",
"wines = wines[1:]\n",
"wines_np = np.array(wines, dtype='float')\n",
"wines_np.shape"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 7. , 0.27, 0.36, ..., 0.45, 8.8 , 6. ],\n",
" [ 6.3 , 0.3 , 0.34, ..., 0.49, 9.5 , 6. ],\n",
" [ 8.1 , 0.28, 0.4 , ..., 0.44, 10.1 , 6. ],\n",
" ...,\n",
" [ 6.5 , 0.24, 0.19, ..., 0.46, 9.4 , 6. ],\n",
" [ 5.5 , 0.29, 0.3 , ..., 0.38, 12.8 , 7. ],\n",
" [ 6. , 0.21, 0.38, ..., 0.32, 11.8 , 6. ]])"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# printing out wines 2-D array\n",
"wines_np"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0. 0.]\n",
" [0. 0.]]\n"
]
}
],
"source": [
"# creating numpy array with all zero elements\n",
"print np.zeros((2,2), dtype='float')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0.79301112 0.95735914]\n",
" [0.29987175 0.96456405]]\n"
]
}
],
"source": [
"# creating numpy array with all random numbers\n",
"print np.random.rand(2,2)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"# using numpy to read dataset\n",
"wines = np.genfromtxt(\n",
" os.path.abspath(os.path.join(DATA_DIR, 'day7/winequality-white.csv')), \n",
" delimiter=\";\", \n",
" skip_header=1\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ True, True, True, ..., True, True, True],\n",
" [ True, True, True, ..., True, True, True],\n",
" [ True, True, True, ..., True, True, True],\n",
" ...,\n",
" [ True, True, True, ..., True, True, True],\n",
" [ True, True, True, ..., True, True, True],\n",
" [ True, True, True, ..., True, True, True]])"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wines == wines_np"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.28\n",
"True\n"
]
}
],
"source": [
"# accessing the value for 3rd row 2nd column of wines\n",
"print wines[2, 1]\n",
"print wines[2, 1] == wines_np[2, 1]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([0.36, 0.34, 0.4 , 0.32])"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# we would like to access 4rows from top of 3rd column\n",
"# wines[start:end, column_index]\n",
"# since the index start from zero; so slicing excludes 4 and finds out result from 0, 1, 2, 3\n",
"wines[:4,2]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([10., 10., 10., 10.])"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# we will override the existing value of 2nd column to 10.0 for all the rows\n",
"wines[:, 2] = 10.0\n",
"wines[:4, 2]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([0.28855438, 0.95129591, 0.80747318, 0.89765623, 0.98632739])"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# creating 1-D array in numpy\n",
"random_1d = np.random.rand(5)\n",
"random_1d"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# creating 3-D numpy array\n",
"random_3d = np.random.rand(2,4,3)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(2, 4, 3)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# take this shape as any thing for 2 years across 4 quarters per month in that quarter\n",
"#2x4x3 = 24 months\n",
"random_3d.shape"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 7, 0, 10, ..., 0, 8, 6],\n",
" [ 6, 0, 10, ..., 0, 9, 6],\n",
" [ 8, 0, 10, ..., 0, 10, 6],\n",
" ...,\n",
" [ 6, 0, 10, ..., 0, 9, 6],\n",
" [ 5, 0, 10, ..., 0, 12, 7],\n",
" [ 6, 0, 10, ..., 0, 11, 6]])"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Data types in numpy\n",
"# converting wines to type=int\n",
"wines.astype('int')"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[6. 6. 6. ... 6. 7. 6.]\n",
"[7. 7. 7. ... 7. 8. 7.]\n"
]
}
],
"source": [
"# addition to any column across all rows\n",
"# as shows below all the remaining mathematical operations can be done\n",
"print wines[:, 11]\n",
"print wines[:, 11] + 1"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([36., 36., 36., ..., 36., 49., 36.])"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# multiplying 2 columns\n",
"# examples show the square of 12th column\n",
"wines[:, 11] * wines[: , 11]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"28790.0"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# sum any column across all rows\n",
"wines[:, 11].sum(axis=0)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"5.87790935075541"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wines[:, 11].mean() #std, min, max are many other methods for fast stats computation"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 1
}