Skip to content

Instantly share code, notes, and snippets.

@mde-2590

mde-2590/Data Wrangling in Python.ipynb

Created May 26, 2019 16:41
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save mde-2590/52bdd7015ff5194ea192e509b92da2d6 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save mde-2590/52bdd7015ff5194ea192e509b92da2d6 to your computer and use it in GitHub Desktop.
Download ZIP
Created on Cognitive Class Labs
Display the source blob
Display the rendered blob
Raw
Data Wrangling in Python.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import matplotlib.pylab as plt"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"filename = \"https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/DA0101EN/auto.csv\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"headers = [\"symboling\",\"normalized-losses\",\"make\",\"fuel-type\",\"aspiration\", \"num-of-doors\",\"body-style\",\n",
" \"drive-wheels\",\"engine-location\",\"wheel-base\", \"length\",\"width\",\"height\",\"curb-weight\",\"engine-type\",\n",
" \"num-of-cylinders\", \"engine-size\",\"fuel-system\",\"bore\",\"stroke\",\"compression-ratio\",\"horsepower\",\n",
" \"peak-rpm\",\"city-mpg\",\"highway-mpg\",\"price\"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(filename, names = headers)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>engine-size</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>?</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>13495</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>?</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>?</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>152</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000</td>\n",
" <td>19</td>\n",
" <td>26</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>109</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500</td>\n",
" <td>24</td>\n",
" <td>30</td>\n",
" <td>13950</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>136</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500</td>\n",
" <td>18</td>\n",
" <td>22</td>\n",
" <td>17450</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration num-of-doors \\\n",
"0 3 ? alfa-romero gas std two \n",
"1 3 ? alfa-romero gas std two \n",
"2 1 ? alfa-romero gas std two \n",
"3 2 164 audi gas std four \n",
"4 2 164 audi gas std four \n",
"\n",
" body-style drive-wheels engine-location wheel-base ... engine-size \\\n",
"0 convertible rwd front 88.6 ... 130 \n",
"1 convertible rwd front 88.6 ... 130 \n",
"2 hatchback rwd front 94.5 ... 152 \n",
"3 sedan fwd front 99.8 ... 109 \n",
"4 sedan 4wd front 99.4 ... 136 \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm city-mpg \\\n",
"0 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"1 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"2 mpfi 2.68 3.47 9.0 154 5000 19 \n",
"3 mpfi 3.19 3.40 10.0 102 5500 24 \n",
"4 mpfi 3.19 3.40 8.0 115 5500 18 \n",
"\n",
" highway-mpg price \n",
"0 27 13495 \n",
"1 27 16500 \n",
"2 26 16500 \n",
"3 30 13950 \n",
"4 22 17450 \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# To see what the data set looks like, we'll use the head() method.\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>engine-size</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>NaN</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>13495</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>NaN</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>152</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000</td>\n",
" <td>19</td>\n",
" <td>26</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>109</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500</td>\n",
" <td>24</td>\n",
" <td>30</td>\n",
" <td>13950</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>136</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500</td>\n",
" <td>18</td>\n",
" <td>22</td>\n",
" <td>17450</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration num-of-doors \\\n",
"0 3 NaN alfa-romero gas std two \n",
"1 3 NaN alfa-romero gas std two \n",
"2 1 NaN alfa-romero gas std two \n",
"3 2 164 audi gas std four \n",
"4 2 164 audi gas std four \n",
"\n",
" body-style drive-wheels engine-location wheel-base ... engine-size \\\n",
"0 convertible rwd front 88.6 ... 130 \n",
"1 convertible rwd front 88.6 ... 130 \n",
"2 hatchback rwd front 94.5 ... 152 \n",
"3 sedan fwd front 99.8 ... 109 \n",
"4 sedan 4wd front 99.4 ... 136 \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm city-mpg \\\n",
"0 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"1 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"2 mpfi 2.68 3.47 9.0 154 5000 19 \n",
"3 mpfi 3.19 3.40 10.0 102 5500 24 \n",
"4 mpfi 3.19 3.40 8.0 115 5500 18 \n",
"\n",
" highway-mpg price \n",
"0 27 13495 \n",
"1 27 16500 \n",
"2 26 16500 \n",
"3 30 13950 \n",
"4 22 17450 \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import numpy as np\n",
"\n",
"# replace \"?\" to NaN\n",
"df.replace(\"?\", np.nan, inplace = True)\n",
"df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>engine-size</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration num-of-doors \\\n",
"0 False True False False False False \n",
"1 False True False False False False \n",
"2 False True False False False False \n",
"3 False False False False False False \n",
"4 False False False False False False \n",
"\n",
" body-style drive-wheels engine-location wheel-base ... engine-size \\\n",
"0 False False False False ... False \n",
"1 False False False False ... False \n",
"2 False False False False ... False \n",
"3 False False False False ... False \n",
"4 False False False False ... False \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm \\\n",
"0 False False False False False False \n",
"1 False False False False False False \n",
"2 False False False False False False \n",
"3 False False False False False False \n",
"4 False False False False False False \n",
"\n",
" city-mpg highway-mpg price \n",
"0 False False False \n",
"1 False False False \n",
"2 False False False \n",
"3 False False False \n",
"4 False False False \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_data = df.isnull()\n",
"missing_data.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"symboling\n",
"False 205\n",
"Name: symboling, dtype: int64\n",
"\n",
"normalized-losses\n",
"False 164\n",
"True 41\n",
"Name: normalized-losses, dtype: int64\n",
"\n",
"make\n",
"False 205\n",
"Name: make, dtype: int64\n",
"\n",
"fuel-type\n",
"False 205\n",
"Name: fuel-type, dtype: int64\n",
"\n",
"aspiration\n",
"False 205\n",
"Name: aspiration, dtype: int64\n",
"\n",
"num-of-doors\n",
"False 203\n",
"True 2\n",
"Name: num-of-doors, dtype: int64\n",
"\n",
"body-style\n",
"False 205\n",
"Name: body-style, dtype: int64\n",
"\n",
"drive-wheels\n",
"False 205\n",
"Name: drive-wheels, dtype: int64\n",
"\n",
"engine-location\n",
"False 205\n",
"Name: engine-location, dtype: int64\n",
"\n",
"wheel-base\n",
"False 205\n",
"Name: wheel-base, dtype: int64\n",
"\n",
"length\n",
"False 205\n",
"Name: length, dtype: int64\n",
"\n",
"width\n",
"False 205\n",
"Name: width, dtype: int64\n",
"\n",
"height\n",
"False 205\n",
"Name: height, dtype: int64\n",
"\n",
"curb-weight\n",
"False 205\n",
"Name: curb-weight, dtype: int64\n",
"\n",
"engine-type\n",
"False 205\n",
"Name: engine-type, dtype: int64\n",
"\n",
"num-of-cylinders\n",
"False 205\n",
"Name: num-of-cylinders, dtype: int64\n",
"\n",
"engine-size\n",
"False 205\n",
"Name: engine-size, dtype: int64\n",
"\n",
"fuel-system\n",
"False 205\n",
"Name: fuel-system, dtype: int64\n",
"\n",
"bore\n",
"False 201\n",
"True 4\n",
"Name: bore, dtype: int64\n",
"\n",
"stroke\n",
"False 201\n",
"True 4\n",
"Name: stroke, dtype: int64\n",
"\n",
"compression-ratio\n",
"False 205\n",
"Name: compression-ratio, dtype: int64\n",
"\n",
"horsepower\n",
"False 203\n",
"True 2\n",
"Name: horsepower, dtype: int64\n",
"\n",
"peak-rpm\n",
"False 203\n",
"True 2\n",
"Name: peak-rpm, dtype: int64\n",
"\n",
"city-mpg\n",
"False 205\n",
"Name: city-mpg, dtype: int64\n",
"\n",
"highway-mpg\n",
"False 205\n",
"Name: highway-mpg, dtype: int64\n",
"\n",
"price\n",
"False 201\n",
"True 4\n",
"Name: price, dtype: int64\n",
"\n"
]
}
],
"source": [
"for column in missing_data.columns.values.tolist():\n",
" print(column)\n",
" print (missing_data[column].value_counts())\n",
" print(\"\") "
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Average of normalized-losses: 122.0\n"
]
}
],
"source": [
"avg_norm_loss = df[\"normalized-losses\"].astype(\"float\").mean(axis=0)\n",
"print(\"Average of normalized-losses:\", avg_norm_loss)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"df[\"normalized-losses\"].replace(np.nan, avg_norm_loss, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Average of bore: 3.3297512437810943\n"
]
}
],
"source": [
"avg_bore=df['bore'].astype('float').mean(axis=0)\n",
"print(\"Average of bore:\", avg_bore)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"df[\"bore\"].replace(np.nan, avg_bore, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Question #1: \n",
"According to the example above, replace NaN in \"stroke\" column by mean."
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Average of stroke: 3.255422885572139\n"
]
}
],
"source": [
"# calculate the mean vaule for \"stroke\" column\n",
"avg_stroke = df[\"stroke\"].astype(\"float\").mean(axis = 0)\n",
"print(\"Average of stroke:\", avg_stroke)\n",
"\n",
"# replace NaN by mean value in \"stroke\" column\n",
"df[\"stroke\"].replace(np.nan, avg_stroke, inplace = True)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Average horsepower: 104.25615763546797\n"
]
}
],
"source": [
"#Calculate the mean value for the 'horsepower' column:\n",
" \n",
"avg_horsepower = df['horsepower'].astype('float').mean(axis=0)\n",
"print(\"Average horsepower:\", avg_horsepower)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"#Replace \"NaN\" by mean value:\n",
"\n",
"df['horsepower'].replace(np.nan, avg_horsepower, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Average peak rpm: 5125.369458128079\n"
]
}
],
"source": [
"#Calculate the mean value for 'peak-rpm' column:\n",
"\n",
"avg_peakrpm=df['peak-rpm'].astype('float').mean(axis=0)\n",
"print(\"Average peak rpm:\", avg_peakrpm)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"#Replace NaN by mean value:\n",
"\n",
"df['peak-rpm'].replace(np.nan, avg_peakrpm, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"four 114\n",
"two 89\n",
"Name: num-of-doors, dtype: int64"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#To see which values are present in a particular column, we can use the \".value_counts()\" method:\n",
"\n",
"df['num-of-doors'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'four'"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['num-of-doors'].value_counts().idxmax()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"#replace the missing 'num-of-doors' values by the most frequent \n",
"\n",
"df[\"num-of-doors\"].replace(np.nan, \"four\", inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# simply drop whole row with NaN in \"price\" column\n",
"\n",
"df.dropna(subset=[\"price\"], axis=0, inplace=True)\n",
"\n",
"# reset index, because we droped two rows\n",
"\n",
"df.reset_index(drop=True, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>engine-size</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>13495</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>152</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000</td>\n",
" <td>19</td>\n",
" <td>26</td>\n",
" <td>16500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>109</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500</td>\n",
" <td>24</td>\n",
" <td>30</td>\n",
" <td>13950</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>136</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500</td>\n",
" <td>18</td>\n",
" <td>22</td>\n",
" <td>17450</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration num-of-doors \\\n",
"0 3 122 alfa-romero gas std two \n",
"1 3 122 alfa-romero gas std two \n",
"2 1 122 alfa-romero gas std two \n",
"3 2 164 audi gas std four \n",
"4 2 164 audi gas std four \n",
"\n",
" body-style drive-wheels engine-location wheel-base ... engine-size \\\n",
"0 convertible rwd front 88.6 ... 130 \n",
"1 convertible rwd front 88.6 ... 130 \n",
"2 hatchback rwd front 94.5 ... 152 \n",
"3 sedan fwd front 99.8 ... 109 \n",
"4 sedan 4wd front 99.4 ... 136 \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm city-mpg \\\n",
"0 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"1 mpfi 3.47 2.68 9.0 111 5000 21 \n",
"2 mpfi 2.68 3.47 9.0 154 5000 19 \n",
"3 mpfi 3.19 3.40 10.0 102 5500 24 \n",
"4 mpfi 3.19 3.40 8.0 115 5500 18 \n",
"\n",
" highway-mpg price \n",
"0 27 13495 \n",
"1 27 16500 \n",
"2 26 16500 \n",
"3 30 13950 \n",
"4 22 17450 \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"symboling int64\n",
"normalized-losses object\n",
"make object\n",
"fuel-type object\n",
"aspiration object\n",
"num-of-doors object\n",
"body-style object\n",
"drive-wheels object\n",
"engine-location object\n",
"wheel-base float64\n",
"length float64\n",
"width float64\n",
"height float64\n",
"curb-weight int64\n",
"engine-type object\n",
"num-of-cylinders object\n",
"engine-size int64\n",
"fuel-system object\n",
"bore object\n",
"stroke object\n",
"compression-ratio float64\n",
"horsepower object\n",
"peak-rpm object\n",
"city-mpg int64\n",
"highway-mpg int64\n",
"price object\n",
"dtype: object"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#data types for each column\n",
"\n",
"df.dtypes"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"#Convert data types to proper format\n",
"\n",
"df[[\"bore\", \"stroke\"]] = df[[\"bore\", \"stroke\"]].astype(\"float\")\n",
"df[[\"normalized-losses\"]] = df[[\"normalized-losses\"]].astype(\"int\")\n",
"df[[\"price\"]] = df[[\"price\"]].astype(\"float\")\n",
"df[[\"peak-rpm\"]] = df[[\"peak-rpm\"]].astype(\"float\")"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"symboling int64\n",
"normalized-losses int64\n",
"make object\n",
"fuel-type object\n",
"aspiration object\n",
"num-of-doors object\n",
"body-style object\n",
"drive-wheels object\n",
"engine-location object\n",
"wheel-base float64\n",
"length float64\n",
"width float64\n",
"height float64\n",
"curb-weight int64\n",
"engine-type object\n",
"num-of-cylinders object\n",
"engine-size int64\n",
"fuel-system object\n",
"bore float64\n",
"stroke float64\n",
"compression-ratio float64\n",
"horsepower object\n",
"peak-rpm float64\n",
"city-mpg int64\n",
"highway-mpg int64\n",
"price float64\n",
"dtype: object"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#List the columns after the conversion\n",
"\n",
"df.dtypes"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>engine-size</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>13495.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>130</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>16500.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>152</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000.0</td>\n",
" <td>19</td>\n",
" <td>26</td>\n",
" <td>16500.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>109</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500.0</td>\n",
" <td>24</td>\n",
" <td>30</td>\n",
" <td>13950.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>136</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500.0</td>\n",
" <td>18</td>\n",
" <td>22</td>\n",
" <td>17450.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration \\\n",
"0 3 122 alfa-romero gas std \n",
"1 3 122 alfa-romero gas std \n",
"2 1 122 alfa-romero gas std \n",
"3 2 164 audi gas std \n",
"4 2 164 audi gas std \n",
"\n",
" num-of-doors body-style drive-wheels engine-location wheel-base ... \\\n",
"0 two convertible rwd front 88.6 ... \n",
"1 two convertible rwd front 88.6 ... \n",
"2 two hatchback rwd front 94.5 ... \n",
"3 four sedan fwd front 99.8 ... \n",
"4 four sedan 4wd front 99.4 ... \n",
"\n",
" engine-size fuel-system bore stroke compression-ratio horsepower \\\n",
"0 130 mpfi 3.47 2.68 9.0 111 \n",
"1 130 mpfi 3.47 2.68 9.0 111 \n",
"2 152 mpfi 2.68 3.47 9.0 154 \n",
"3 109 mpfi 3.19 3.40 10.0 102 \n",
"4 136 mpfi 3.19 3.40 8.0 115 \n",
"\n",
" peak-rpm city-mpg highway-mpg price \n",
"0 5000.0 21 27 13495.0 \n",
"1 5000.0 21 27 16500.0 \n",
"2 5000.0 19 26 16500.0 \n",
"3 5500.0 24 30 13950.0 \n",
"4 5500.0 18 22 17450.0 \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"# Convert mpg to L/100km by mathematical operation (235 divided by mpg)\n",
"df['city-L/100km'] = 235/df[\"city-mpg\"]"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" <th>city-L/100km</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>13495.0</td>\n",
" <td>11.190476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27</td>\n",
" <td>16500.0</td>\n",
" <td>11.190476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000.0</td>\n",
" <td>19</td>\n",
" <td>26</td>\n",
" <td>16500.0</td>\n",
" <td>12.368421</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500.0</td>\n",
" <td>24</td>\n",
" <td>30</td>\n",
" <td>13950.0</td>\n",
" <td>9.791667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500.0</td>\n",
" <td>18</td>\n",
" <td>22</td>\n",
" <td>17450.0</td>\n",
" <td>13.055556</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration \\\n",
"0 3 122 alfa-romero gas std \n",
"1 3 122 alfa-romero gas std \n",
"2 1 122 alfa-romero gas std \n",
"3 2 164 audi gas std \n",
"4 2 164 audi gas std \n",
"\n",
" num-of-doors body-style drive-wheels engine-location wheel-base ... \\\n",
"0 two convertible rwd front 88.6 ... \n",
"1 two convertible rwd front 88.6 ... \n",
"2 two hatchback rwd front 94.5 ... \n",
"3 four sedan fwd front 99.8 ... \n",
"4 four sedan 4wd front 99.4 ... \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm city-mpg \\\n",
"0 mpfi 3.47 2.68 9.0 111 5000.0 21 \n",
"1 mpfi 3.47 2.68 9.0 111 5000.0 21 \n",
"2 mpfi 2.68 3.47 9.0 154 5000.0 19 \n",
"3 mpfi 3.19 3.40 10.0 102 5500.0 24 \n",
"4 mpfi 3.19 3.40 8.0 115 5500.0 18 \n",
"\n",
" highway-mpg price city-L/100km \n",
"0 27 13495.0 11.190476 \n",
"1 27 16500.0 11.190476 \n",
"2 26 16500.0 12.368421 \n",
"3 30 13950.0 9.791667 \n",
"4 22 17450.0 13.055556 \n",
"\n",
"[5 rows x 27 columns]"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check your transformed data \n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Question #2: \n",
"According to the example above, transform mpg to L/100km in the column of \"highway-mpg\", and change the name of column to \"highway-L/100km\"."
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"# transform mpg to L/100km by mathematical operation (235 divided by mpg)\n",
"df[\"highway-mpg\"] = 235/df[\"highway-mpg\"]"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"# rename column name from \"highway-mpg\" to \"highway-L/100km\"\n",
"df.rename(columns={'\"highway-mpg\"':'highway-L/100km'}, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>fuel-type</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>...</th>\n",
" <th>fuel-system</th>\n",
" <th>bore</th>\n",
" <th>stroke</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" <th>city-L/100km</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27.0</td>\n",
" <td>13495.0</td>\n",
" <td>11.190476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.47</td>\n",
" <td>2.68</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27.0</td>\n",
" <td>16500.0</td>\n",
" <td>11.190476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>2.68</td>\n",
" <td>3.47</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000.0</td>\n",
" <td>19</td>\n",
" <td>26.0</td>\n",
" <td>16500.0</td>\n",
" <td>12.368421</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500.0</td>\n",
" <td>24</td>\n",
" <td>30.0</td>\n",
" <td>13950.0</td>\n",
" <td>9.791667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>gas</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>...</td>\n",
" <td>mpfi</td>\n",
" <td>3.19</td>\n",
" <td>3.40</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500.0</td>\n",
" <td>18</td>\n",
" <td>22.0</td>\n",
" <td>17450.0</td>\n",
" <td>13.055556</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make fuel-type aspiration \\\n",
"0 3 122 alfa-romero gas std \n",
"1 3 122 alfa-romero gas std \n",
"2 1 122 alfa-romero gas std \n",
"3 2 164 audi gas std \n",
"4 2 164 audi gas std \n",
"\n",
" num-of-doors body-style drive-wheels engine-location wheel-base ... \\\n",
"0 two convertible rwd front 88.6 ... \n",
"1 two convertible rwd front 88.6 ... \n",
"2 two hatchback rwd front 94.5 ... \n",
"3 four sedan fwd front 99.8 ... \n",
"4 four sedan 4wd front 99.4 ... \n",
"\n",
" fuel-system bore stroke compression-ratio horsepower peak-rpm city-mpg \\\n",
"0 mpfi 3.47 2.68 9.0 111 5000.0 21 \n",
"1 mpfi 3.47 2.68 9.0 111 5000.0 21 \n",
"2 mpfi 2.68 3.47 9.0 154 5000.0 19 \n",
"3 mpfi 3.19 3.40 10.0 102 5500.0 24 \n",
"4 mpfi 3.19 3.40 8.0 115 5500.0 18 \n",
"\n",
" highway-mpg price city-L/100km \n",
"0 27.0 13495.0 11.190476 \n",
"1 27.0 16500.0 11.190476 \n",
"2 26.0 16500.0 12.368421 \n",
"3 30.0 13950.0 9.791667 \n",
"4 22.0 17450.0 13.055556 \n",
"\n",
"[5 rows x 27 columns]"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check your transformed data \n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"# replace (original value) by (original value)/(maximum value)\n",
"df['length'] = df['length']/df['length'].max()\n",
"df['width'] = df['width']/df['width'].max()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Questiont #3: \n",
"According to the example above, normalize the column \"height\"."
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>length</th>\n",
" <th>width</th>\n",
" <th>height</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.811148</td>\n",
" <td>0.890278</td>\n",
" <td>0.816054</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.811148</td>\n",
" <td>0.890278</td>\n",
" <td>0.816054</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.822681</td>\n",
" <td>0.909722</td>\n",
" <td>0.876254</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.848630</td>\n",
" <td>0.919444</td>\n",
" <td>0.908027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.848630</td>\n",
" <td>0.922222</td>\n",
" <td>0.908027</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" length width height\n",
"0 0.811148 0.890278 0.816054\n",
"1 0.811148 0.890278 0.816054\n",
"2 0.822681 0.909722 0.876254\n",
"3 0.848630 0.919444 0.908027\n",
"4 0.848630 0.922222 0.908027"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['height'] = df['height']/df['height'].max() \n",
"# show the scaled columns\n",
"df[[\"length\",\"width\",\"height\"]].head()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Binning Data In Pandas"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"df[\"horsepower\"]=df[\"horsepower\"].astype(int, copy=True)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"#Plot the histogram of horspower, to see what the distribution of horsepower looks like.\n"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0.5, 1.0, 'horsepower bins')"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"%matplotlib inline\n",
"import matplotlib as plt\n",
"from matplotlib import pyplot\n",
"plt.pyplot.hist(df[\"horsepower\"])\n",
"\n",
"# set x/y labels and plot title\n",
"plt.pyplot.xlabel(\"horsepower\")\n",
"plt.pyplot.ylabel(\"count\")\n",
"plt.pyplot.title(\"horsepower bins\")"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 48. , 119.33333333, 190.66666667, 262. ])"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bins = np.linspace(min(df[\"horsepower\"]), max(df[\"horsepower\"]), 4)\n",
"bins"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [],
"source": [
"group_names = ['Low', 'Medium', 'High']"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>horsepower</th>\n",
" <th>horsepower-binned</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>111</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>111</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>154</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>102</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>115</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>110</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>110</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>110</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>140</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>101</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>101</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>121</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>121</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>121</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>182</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>182</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>182</td>\n",
" <td>Medium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>48</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>70</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>70</td>\n",
" <td>Low</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" horsepower horsepower-binned\n",
"0 111 Low\n",
"1 111 Low\n",
"2 154 Medium\n",
"3 102 Low\n",
"4 115 Low\n",
"5 110 Low\n",
"6 110 Low\n",
"7 110 Low\n",
"8 140 Medium\n",
"9 101 Low\n",
"10 101 Low\n",
"11 121 Medium\n",
"12 121 Medium\n",
"13 121 Medium\n",
"14 182 Medium\n",
"15 182 Medium\n",
"16 182 Medium\n",
"17 48 Low\n",
"18 70 Low\n",
"19 70 Low"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Apply the function \"cut\" the determine what each value of \"df['horsepower']\" belongs to.\n",
"\n",
"df['horsepower-binned'] = pd.cut(df['horsepower'], bins, labels=group_names, include_lowest=True )\n",
"df[['horsepower','horsepower-binned']].head(20)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Low 153\n",
"Medium 43\n",
"High 5\n",
"Name: horsepower-binned, dtype: int64"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Lets see the number of vehicles in each bin\n",
"\n",
"df[\"horsepower-binned\"].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
"#Plot the distribution of each bin"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0.5, 1.0, 'horsepower bins')"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"%matplotlib inline\n",
"import matplotlib as plt\n",
"from matplotlib import pyplot\n",
"pyplot.bar(group_names, df[\"horsepower-binned\"].value_counts())\n",
"\n",
"# set x/y labels and plot title\n",
"plt.pyplot.xlabel(\"horsepower\")\n",
"plt.pyplot.ylabel(\"count\")\n",
"plt.pyplot.title(\"horsepower bins\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Bins visualization\n",
"Normally, a histogram is used to visualize the distribution of bins we created above."
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Text(0.5, 1.0, 'horsepower bins')"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"%matplotlib inline\n",
"import matplotlib as plt\n",
"from matplotlib import pyplot\n",
"\n",
"a = (0,1,2)\n",
"\n",
"# draw historgram of attribute \"horsepower\" with bins = 3\n",
"plt.pyplot.hist(df[\"horsepower\"], bins = 3)\n",
"\n",
"# set x/y labels and plot title\n",
"plt.pyplot.xlabel(\"horsepower\")\n",
"plt.pyplot.ylabel(\"count\")\n",
"plt.pyplot.title(\"horsepower bins\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Indicator variable (or dummy variable)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [],
"source": [
"#Use the panda's method 'get_dummies' to assign numerical values to different categories of fuel type."
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['symboling', 'normalized-losses', 'make', 'fuel-type', 'aspiration',\n",
" 'num-of-doors', 'body-style', 'drive-wheels', 'engine-location',\n",
" 'wheel-base', 'length', 'width', 'height', 'curb-weight', 'engine-type',\n",
" 'num-of-cylinders', 'engine-size', 'fuel-system', 'bore', 'stroke',\n",
" 'compression-ratio', 'horsepower', 'peak-rpm', 'city-mpg',\n",
" 'highway-mpg', 'price', 'city-L/100km', 'horsepower-binned'],\n",
" dtype='object')"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": [
"#Get indicator variables and assign it to data frame \"dummy_variable_1\""
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>diesel</th>\n",
" <th>gas</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" diesel gas\n",
"0 0 1\n",
"1 0 1\n",
"2 0 1\n",
"3 0 1\n",
"4 0 1"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dummy_variable_1 = pd.get_dummies(df[\"fuel-type\"])\n",
"dummy_variable_1.head()"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {},
"outputs": [],
"source": [
"#Change column names for clarity"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>diesel</th>\n",
" <th>gas</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" diesel gas\n",
"0 0 1\n",
"1 0 1\n",
"2 0 1\n",
"3 0 1\n",
"4 0 1"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dummy_variable_1.rename(columns={'fuel-type-diesel':'gas', 'fuel-type-diesel':'diesel'}, inplace=True)\n",
"dummy_variable_1.head()"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [],
"source": [
"#The value 0 to represents \"gas\" and 1 to represent \"diesel\" in the column \"fuel-type\". We will now insert this column back into our original dataset."
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
"# merge data frame \"df\" and \"dummy_variable_1\" \n",
"df = pd.concat([df, dummy_variable_1], axis=1)\n",
"\n",
"# drop original column \"fuel-type\" from \"df\"\n",
"df.drop(\"fuel-type\", axis = 1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>symboling</th>\n",
" <th>normalized-losses</th>\n",
" <th>make</th>\n",
" <th>aspiration</th>\n",
" <th>num-of-doors</th>\n",
" <th>body-style</th>\n",
" <th>drive-wheels</th>\n",
" <th>engine-location</th>\n",
" <th>wheel-base</th>\n",
" <th>length</th>\n",
" <th>...</th>\n",
" <th>compression-ratio</th>\n",
" <th>horsepower</th>\n",
" <th>peak-rpm</th>\n",
" <th>city-mpg</th>\n",
" <th>highway-mpg</th>\n",
" <th>price</th>\n",
" <th>city-L/100km</th>\n",
" <th>horsepower-binned</th>\n",
" <th>diesel</th>\n",
" <th>gas</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>0.811148</td>\n",
" <td>...</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27.0</td>\n",
" <td>13495.0</td>\n",
" <td>11.190476</td>\n",
" <td>Low</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>convertible</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>88.6</td>\n",
" <td>0.811148</td>\n",
" <td>...</td>\n",
" <td>9.0</td>\n",
" <td>111</td>\n",
" <td>5000.0</td>\n",
" <td>21</td>\n",
" <td>27.0</td>\n",
" <td>16500.0</td>\n",
" <td>11.190476</td>\n",
" <td>Low</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>122</td>\n",
" <td>alfa-romero</td>\n",
" <td>std</td>\n",
" <td>two</td>\n",
" <td>hatchback</td>\n",
" <td>rwd</td>\n",
" <td>front</td>\n",
" <td>94.5</td>\n",
" <td>0.822681</td>\n",
" <td>...</td>\n",
" <td>9.0</td>\n",
" <td>154</td>\n",
" <td>5000.0</td>\n",
" <td>19</td>\n",
" <td>26.0</td>\n",
" <td>16500.0</td>\n",
" <td>12.368421</td>\n",
" <td>Medium</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>fwd</td>\n",
" <td>front</td>\n",
" <td>99.8</td>\n",
" <td>0.848630</td>\n",
" <td>...</td>\n",
" <td>10.0</td>\n",
" <td>102</td>\n",
" <td>5500.0</td>\n",
" <td>24</td>\n",
" <td>30.0</td>\n",
" <td>13950.0</td>\n",
" <td>9.791667</td>\n",
" <td>Low</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>164</td>\n",
" <td>audi</td>\n",
" <td>std</td>\n",
" <td>four</td>\n",
" <td>sedan</td>\n",
" <td>4wd</td>\n",
" <td>front</td>\n",
" <td>99.4</td>\n",
" <td>0.848630</td>\n",
" <td>...</td>\n",
" <td>8.0</td>\n",
" <td>115</td>\n",
" <td>5500.0</td>\n",
" <td>18</td>\n",
" <td>22.0</td>\n",
" <td>17450.0</td>\n",
" <td>13.055556</td>\n",
" <td>Low</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 29 columns</p>\n",
"</div>"
],
"text/plain": [
" symboling normalized-losses make aspiration num-of-doors \\\n",
"0 3 122 alfa-romero std two \n",
"1 3 122 alfa-romero std two \n",
"2 1 122 alfa-romero std two \n",
"3 2 164 audi std four \n",
"4 2 164 audi std four \n",
"\n",
" body-style drive-wheels engine-location wheel-base length ... \\\n",
"0 convertible rwd front 88.6 0.811148 ... \n",
"1 convertible rwd front 88.6 0.811148 ... \n",
"2 hatchback rwd front 94.5 0.822681 ... \n",
"3 sedan fwd front 99.8 0.848630 ... \n",
"4 sedan 4wd front 99.4 0.848630 ... \n",
"\n",
" compression-ratio horsepower peak-rpm city-mpg highway-mpg price \\\n",
"0 9.0 111 5000.0 21 27.0 13495.0 \n",
"1 9.0 111 5000.0 21 27.0 16500.0 \n",
"2 9.0 154 5000.0 19 26.0 16500.0 \n",
"3 10.0 102 5500.0 24 30.0 13950.0 \n",
"4 8.0 115 5500.0 18 22.0 17450.0 \n",
"\n",
" city-L/100km horsepower-binned diesel gas \n",
"0 11.190476 Low 0 1 \n",
"1 11.190476 Low 0 1 \n",
"2 12.368421 Medium 0 1 \n",
"3 9.791667 Low 0 1 \n",
"4 13.055556 Low 0 1 \n",
"\n",
"[5 rows x 29 columns]"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Question #4: \n",
"As above, create indicator variable to the column of \"aspiration\": \"std\" to 0, while \"turbo\" to 1."
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [],
"source": [
"# get indicator variables of aspiration and assign it to data frame \"dummy_variable_2\"\n",
"dummy_variable_2 = pd.get_dummies(df['aspiration'])"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
"# change column names for clarity\n",
"dummy_variable_2.rename(columns={'std':'aspiration-std', 'turbo': 'aspiration-turbo'}, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>aspiration-std</th>\n",
" <th>aspiration-turbo</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" aspiration-std aspiration-turbo\n",
"0 1 0\n",
"1 1 0\n",
"2 1 0\n",
"3 1 0\n",
"4 1 0"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# show first 5 instances of data frame \"dummy_variable_1\"\n",
"dummy_variable_2.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Question #5: \n",
"Merge the new dataframe to the original dataframe then drop the column 'aspiration'"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {},
"outputs": [],
"source": [
"#merge the new dataframe to the original datafram\n",
"df = pd.concat([df, dummy_variable_2], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [],
"source": [
"# drop original column \"aspiration\" from \"df\"\n",
"df.drop('aspiration', axis = 1, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Save the new csv"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('clean_df.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment