{
"cells": [
{
"cell_type": "markdown",
"id": "74012e00",
"metadata": {},
"source": [
"# Install and import libraries"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "cd7ae131",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"# Install libraries\n",
"!pip install -q missingno\n",
"!pip install -q pyod\n",
"\n",
"# import libraries\n",
"import missingno as msno\n",
"import pandas as pd\n",
"from pyod.models.knn import KNN"
]
},
{
"cell_type": "markdown",
"id": "acc6fb0f",
"metadata": {},
"source": [
"# Importing the dataset"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "99953ed1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Shape before dropping columns: (330782, 67)\n"
]
},
{
"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>iso_code</th>\n",
" <th>continent</th>\n",
" <th>location</th>\n",
" <th>date</th>\n",
" <th>total_cases</th>\n",
" <th>new_cases</th>\n",
" <th>new_cases_smoothed</th>\n",
" <th>total_deaths</th>\n",
" <th>new_deaths</th>\n",
" <th>new_deaths_smoothed</th>\n",
" <th>...</th>\n",
" <th>male_smokers</th>\n",
" <th>handwashing_facilities</th>\n",
" <th>hospital_beds_per_thousand</th>\n",
" <th>life_expectancy</th>\n",
" <th>human_development_index</th>\n",
" <th>population</th>\n",
" <th>excess_mortality_cumulative_absolute</th>\n",
" <th>excess_mortality_cumulative</th>\n",
" <th>excess_mortality</th>\n",
" <th>excess_mortality_cumulative_per_million</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>Asia</td>\n",
" <td>Afghanistan</td>\n",
" <td>2020-01-03</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>37.75</td>\n",
" <td>0.50</td>\n",
" <td>64.83</td>\n",
" <td>0.51</td>\n",
" <td>41128772.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>Asia</td>\n",
" <td>Afghanistan</td>\n",
" <td>2020-01-04</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>37.75</td>\n",
" <td>0.50</td>\n",
" <td>64.83</td>\n",
" <td>0.51</td>\n",
" <td>41128772.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>Asia</td>\n",
" <td>Afghanistan</td>\n",
" <td>2020-01-05</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>37.75</td>\n",
" <td>0.50</td>\n",
" <td>64.83</td>\n",
" <td>0.51</td>\n",
" <td>41128772.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>Asia</td>\n",
" <td>Afghanistan</td>\n",
" <td>2020-01-06</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>37.75</td>\n",
" <td>0.50</td>\n",
" <td>64.83</td>\n",
" <td>0.51</td>\n",
" <td>41128772.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>Asia</td>\n",
" <td>Afghanistan</td>\n",
" <td>2020-01-07</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>37.75</td>\n",
" <td>0.50</td>\n",
" <td>64.83</td>\n",
" <td>0.51</td>\n",
" <td>41128772.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 67 columns</p>\n",
"</div>"
],
"text/plain": [
" iso_code continent location date total_cases new_cases \\\n",
"0 AFG Asia Afghanistan 2020-01-03 NaN 0.00 \n",
"1 AFG Asia Afghanistan 2020-01-04 NaN 0.00 \n",
"2 AFG Asia Afghanistan 2020-01-05 NaN 0.00 \n",
"3 AFG Asia Afghanistan 2020-01-06 NaN 0.00 \n",
"4 AFG Asia Afghanistan 2020-01-07 NaN 0.00 \n",
"\n",
" new_cases_smoothed total_deaths new_deaths new_deaths_smoothed ... \\\n",
"0 NaN NaN 0.00 NaN ... \n",
"1 NaN NaN 0.00 NaN ... \n",
"2 NaN NaN 0.00 NaN ... \n",
"3 NaN NaN 0.00 NaN ... \n",
"4 NaN NaN 0.00 NaN ... \n",
"\n",
" male_smokers handwashing_facilities hospital_beds_per_thousand \\\n",
"0 NaN 37.75 0.50 \n",
"1 NaN 37.75 0.50 \n",
"2 NaN 37.75 0.50 \n",
"3 NaN 37.75 0.50 \n",
"4 NaN 37.75 0.50 \n",
"\n",
" life_expectancy human_development_index population \\\n",
"0 64.83 0.51 41128772.00 \n",
"1 64.83 0.51 41128772.00 \n",
"2 64.83 0.51 41128772.00 \n",
"3 64.83 0.51 41128772.00 \n",
"4 64.83 0.51 41128772.00 \n",
"\n",
" excess_mortality_cumulative_absolute excess_mortality_cumulative \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"\n",
" excess_mortality excess_mortality_cumulative_per_million \n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"\n",
"[5 rows x 67 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Read the dataset\n",
"dataset_path = \"C:\\My\\Top-up Degree\\Data Science\\Data Science - Assignment\\Data set\\Kaggle\\Our World in Data - COVID-19\\owid-covid-data.csv\"\n",
"data = pd.read_csv(dataset_path)\n",
"print(\"Shape before dropping columns:\", data.shape)\n",
"display(data.head(n=5))"
]
},
{
"cell_type": "markdown",
"id": "6d083bab",
"metadata": {},
"source": [
"## Describing the dataset"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "7d31bcf2",
"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>total_cases</th>\n",
" <th>new_cases</th>\n",
" <th>new_cases_smoothed</th>\n",
" <th>total_deaths</th>\n",
" <th>new_deaths</th>\n",
" <th>new_deaths_smoothed</th>\n",
" <th>total_cases_per_million</th>\n",
" <th>new_cases_per_million</th>\n",
" <th>new_cases_smoothed_per_million</th>\n",
" <th>total_deaths_per_million</th>\n",
" <th>...</th>\n",
" <th>male_smokers</th>\n",
" <th>handwashing_facilities</th>\n",
" <th>hospital_beds_per_thousand</th>\n",
" <th>life_expectancy</th>\n",
" <th>human_development_index</th>\n",
" <th>population</th>\n",
" <th>excess_mortality_cumulative_absolute</th>\n",
" <th>excess_mortality_cumulative</th>\n",
" <th>excess_mortality</th>\n",
" <th>excess_mortality_cumulative_per_million</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>2.933000e+05</td>\n",
" <td>3.216330e+05</td>\n",
" <td>3.203740e+05</td>\n",
" <td>2.721740e+05</td>\n",
" <td>321702.000000</td>\n",
" <td>320472.000000</td>\n",
" <td>293300.000000</td>\n",
" <td>321633.000000</td>\n",
" <td>320374.000000</td>\n",
" <td>272174.000000</td>\n",
" <td>...</td>\n",
" <td>189702.000000</td>\n",
" <td>125583.000000</td>\n",
" <td>226326.000000</td>\n",
" <td>304234.000000</td>\n",
" <td>248529.000000</td>\n",
" <td>3.307820e+05</td>\n",
" <td>1.153500e+04</td>\n",
" <td>11535.000000</td>\n",
" <td>11535.000000</td>\n",
" <td>11535.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>6.253904e+06</td>\n",
" <td>1.013110e+04</td>\n",
" <td>1.016799e+04</td>\n",
" <td>8.357613e+04</td>\n",
" <td>91.896227</td>\n",
" <td>92.240686</td>\n",
" <td>95300.478343</td>\n",
" <td>153.109948</td>\n",
" <td>153.681658</td>\n",
" <td>843.644772</td>\n",
" <td>...</td>\n",
" <td>32.910416</td>\n",
" <td>50.790677</td>\n",
" <td>3.097145</td>\n",
" <td>73.716225</td>\n",
" <td>0.722483</td>\n",
" <td>1.282799e+08</td>\n",
" <td>4.933200e+04</td>\n",
" <td>9.635586</td>\n",
" <td>11.815644</td>\n",
" <td>1591.662698</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>3.854149e+07</td>\n",
" <td>1.134175e+05</td>\n",
" <td>9.718695e+04</td>\n",
" <td>4.293215e+05</td>\n",
" <td>761.899876</td>\n",
" <td>597.590018</td>\n",
" <td>145463.270075</td>\n",
" <td>1196.206835</td>\n",
" <td>616.176235</td>\n",
" <td>1079.976631</td>\n",
" <td>...</td>\n",
" <td>13.574225</td>\n",
" <td>31.956510</td>\n",
" <td>2.548339</td>\n",
" <td>7.396354</td>\n",
" <td>0.148987</td>\n",
" <td>6.602098e+08</td>\n",
" <td>1.412464e+05</td>\n",
" <td>12.479665</td>\n",
" <td>25.623475</td>\n",
" <td>1894.037851</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>...</td>\n",
" <td>7.700000</td>\n",
" <td>1.188000</td>\n",
" <td>0.100000</td>\n",
" <td>53.280000</td>\n",
" <td>0.394000</td>\n",
" <td>4.700000e+01</td>\n",
" <td>-3.772610e+04</td>\n",
" <td>-44.230000</td>\n",
" <td>-95.920000</td>\n",
" <td>-2142.340300</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>7.474000e+03</td>\n",
" <td>0.000000e+00</td>\n",
" <td>5.710000e-01</td>\n",
" <td>1.250000e+02</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>2273.895000</td>\n",
" <td>0.000000</td>\n",
" <td>0.120000</td>\n",
" <td>55.469500</td>\n",
" <td>...</td>\n",
" <td>22.600000</td>\n",
" <td>20.859000</td>\n",
" <td>1.300000</td>\n",
" <td>69.590000</td>\n",
" <td>0.602000</td>\n",
" <td>4.490020e+05</td>\n",
" <td>7.479999e+01</td>\n",
" <td>1.070000</td>\n",
" <td>-1.495000</td>\n",
" <td>46.896362</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>6.538100e+04</td>\n",
" <td>4.000000e+00</td>\n",
" <td>3.007150e+01</td>\n",
" <td>1.250000e+03</td>\n",
" <td>0.000000</td>\n",
" <td>0.143000</td>\n",
" <td>24535.964500</td>\n",
" <td>0.366000</td>\n",
" <td>8.249000</td>\n",
" <td>358.698000</td>\n",
" <td>...</td>\n",
" <td>33.100000</td>\n",
" <td>49.839000</td>\n",
" <td>2.500000</td>\n",
" <td>75.050000</td>\n",
" <td>0.740000</td>\n",
" <td>5.882259e+06</td>\n",
" <td>5.352899e+03</td>\n",
" <td>7.960000</td>\n",
" <td>6.020000</td>\n",
" <td>1021.922500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>6.940385e+05</td>\n",
" <td>3.160000e+02</td>\n",
" <td>5.622860e+02</td>\n",
" <td>1.116475e+04</td>\n",
" <td>3.000000</td>\n",
" <td>5.857000</td>\n",
" <td>122228.212250</td>\n",
" <td>41.737000</td>\n",
" <td>92.141750</td>\n",
" <td>1298.258000</td>\n",
" <td>...</td>\n",
" <td>41.300000</td>\n",
" <td>83.241000</td>\n",
" <td>4.200000</td>\n",
" <td>79.460000</td>\n",
" <td>0.829000</td>\n",
" <td>2.830170e+07</td>\n",
" <td>3.510710e+04</td>\n",
" <td>15.370000</td>\n",
" <td>16.920000</td>\n",
" <td>2615.629150</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>7.689823e+08</td>\n",
" <td>8.401763e+06</td>\n",
" <td>6.402721e+06</td>\n",
" <td>6.953730e+06</td>\n",
" <td>121590.000000</td>\n",
" <td>18214.143000</td>\n",
" <td>737554.506000</td>\n",
" <td>228872.025000</td>\n",
" <td>37241.781000</td>\n",
" <td>6501.224000</td>\n",
" <td>...</td>\n",
" <td>78.100000</td>\n",
" <td>100.000000</td>\n",
" <td>13.800000</td>\n",
" <td>86.750000</td>\n",
" <td>0.957000</td>\n",
" <td>7.975105e+09</td>\n",
" <td>1.281224e+06</td>\n",
" <td>76.550000</td>\n",
" <td>377.430000</td>\n",
" <td>10292.468000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 62 columns</p>\n",
"</div>"
],
"text/plain": [
" total_cases new_cases new_cases_smoothed total_deaths \\\n",
"count 2.933000e+05 3.216330e+05 3.203740e+05 2.721740e+05 \n",
"mean 6.253904e+06 1.013110e+04 1.016799e+04 8.357613e+04 \n",
"std 3.854149e+07 1.134175e+05 9.718695e+04 4.293215e+05 \n",
"min 1.000000e+00 0.000000e+00 0.000000e+00 1.000000e+00 \n",
"25% 7.474000e+03 0.000000e+00 5.710000e-01 1.250000e+02 \n",
"50% 6.538100e+04 4.000000e+00 3.007150e+01 1.250000e+03 \n",
"75% 6.940385e+05 3.160000e+02 5.622860e+02 1.116475e+04 \n",
"max 7.689823e+08 8.401763e+06 6.402721e+06 6.953730e+06 \n",
"\n",
" new_deaths new_deaths_smoothed total_cases_per_million \\\n",
"count 321702.000000 320472.000000 293300.000000 \n",
"mean 91.896227 92.240686 95300.478343 \n",
"std 761.899876 597.590018 145463.270075 \n",
"min 0.000000 0.000000 0.000000 \n",
"25% 0.000000 0.000000 2273.895000 \n",
"50% 0.000000 0.143000 24535.964500 \n",
"75% 3.000000 5.857000 122228.212250 \n",
"max 121590.000000 18214.143000 737554.506000 \n",
"\n",
" new_cases_per_million new_cases_smoothed_per_million \\\n",
"count 321633.000000 320374.000000 \n",
"mean 153.109948 153.681658 \n",
"std 1196.206835 616.176235 \n",
"min 0.000000 0.000000 \n",
"25% 0.000000 0.120000 \n",
"50% 0.366000 8.249000 \n",
"75% 41.737000 92.141750 \n",
"max 228872.025000 37241.781000 \n",
"\n",
" total_deaths_per_million ... male_smokers handwashing_facilities \\\n",
"count 272174.000000 ... 189702.000000 125583.000000 \n",
"mean 843.644772 ... 32.910416 50.790677 \n",
"std 1079.976631 ... 13.574225 31.956510 \n",
"min 0.000000 ... 7.700000 1.188000 \n",
"25% 55.469500 ... 22.600000 20.859000 \n",
"50% 358.698000 ... 33.100000 49.839000 \n",
"75% 1298.258000 ... 41.300000 83.241000 \n",
"max 6501.224000 ... 78.100000 100.000000 \n",
"\n",
" hospital_beds_per_thousand life_expectancy human_development_index \\\n",
"count 226326.000000 304234.000000 248529.000000 \n",
"mean 3.097145 73.716225 0.722483 \n",
"std 2.548339 7.396354 0.148987 \n",
"min 0.100000 53.280000 0.394000 \n",
"25% 1.300000 69.590000 0.602000 \n",
"50% 2.500000 75.050000 0.740000 \n",
"75% 4.200000 79.460000 0.829000 \n",
"max 13.800000 86.750000 0.957000 \n",
"\n",
" population excess_mortality_cumulative_absolute \\\n",
"count 3.307820e+05 1.153500e+04 \n",
"mean 1.282799e+08 4.933200e+04 \n",
"std 6.602098e+08 1.412464e+05 \n",
"min 4.700000e+01 -3.772610e+04 \n",
"25% 4.490020e+05 7.479999e+01 \n",
"50% 5.882259e+06 5.352899e+03 \n",
"75% 2.830170e+07 3.510710e+04 \n",
"max 7.975105e+09 1.281224e+06 \n",
"\n",
" excess_mortality_cumulative excess_mortality \\\n",
"count 11535.000000 11535.000000 \n",
"mean 9.635586 11.815644 \n",
"std 12.479665 25.623475 \n",
"min -44.230000 -95.920000 \n",
"25% 1.070000 -1.495000 \n",
"50% 7.960000 6.020000 \n",
"75% 15.370000 16.920000 \n",
"max 76.550000 377.430000 \n",
"\n",
" excess_mortality_cumulative_per_million \n",
"count 11535.000000 \n",
"mean 1591.662698 \n",
"std 1894.037851 \n",
"min -2142.340300 \n",
"25% 46.896362 \n",
"50% 1021.922500 \n",
"75% 2615.629150 \n",
"max 10292.468000 \n",
"\n",
"[8 rows x 62 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.describe() # print the descriptive statistics"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5ac2c919",
"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>total_cases</th>\n",
" <th>new_cases</th>\n",
" <th>new_cases_smoothed</th>\n",
" <th>total_deaths</th>\n",
" <th>new_deaths</th>\n",
" <th>new_deaths_smoothed</th>\n",
" <th>total_cases_per_million</th>\n",
" <th>new_cases_per_million</th>\n",
" <th>new_cases_smoothed_per_million</th>\n",
" <th>total_deaths_per_million</th>\n",
" <th>...</th>\n",
" <th>male_smokers</th>\n",
" <th>handwashing_facilities</th>\n",
" <th>hospital_beds_per_thousand</th>\n",
" <th>life_expectancy</th>\n",
" <th>human_development_index</th>\n",
" <th>population</th>\n",
" <th>excess_mortality_cumulative_absolute</th>\n",
" <th>excess_mortality_cumulative</th>\n",
" <th>excess_mortality</th>\n",
" <th>excess_mortality_cumulative_per_million</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>293300.00</td>\n",
" <td>321633.00</td>\n",
" <td>320374.00</td>\n",
" <td>272174.00</td>\n",
" <td>321702.00</td>\n",
" <td>320472.00</td>\n",
" <td>293300.00</td>\n",
" <td>321633.00</td>\n",
" <td>320374.00</td>\n",
" <td>272174.00</td>\n",
" <td>...</td>\n",
" <td>189702.00</td>\n",
" <td>125583.00</td>\n",
" <td>226326.00</td>\n",
" <td>304234.00</td>\n",
" <td>248529.00</td>\n",
" <td>330782.00</td>\n",
" <td>11535.00</td>\n",
" <td>11535.00</td>\n",
" <td>11535.00</td>\n",
" <td>11535.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>6253904.17</td>\n",
" <td>10131.10</td>\n",
" <td>10167.99</td>\n",
" <td>83576.13</td>\n",
" <td>91.90</td>\n",
" <td>92.24</td>\n",
" <td>95300.48</td>\n",
" <td>153.11</td>\n",
" <td>153.68</td>\n",
" <td>843.64</td>\n",
" <td>...</td>\n",
" <td>32.91</td>\n",
" <td>50.79</td>\n",
" <td>3.10</td>\n",
" <td>73.72</td>\n",
" <td>0.72</td>\n",
" <td>128279905.10</td>\n",
" <td>49332.00</td>\n",
" <td>9.64</td>\n",
" <td>11.82</td>\n",
" <td>1591.66</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>38541489.37</td>\n",
" <td>113417.45</td>\n",
" <td>97186.95</td>\n",
" <td>429321.51</td>\n",
" <td>761.90</td>\n",
" <td>597.59</td>\n",
" <td>145463.27</td>\n",
" <td>1196.21</td>\n",
" <td>616.18</td>\n",
" <td>1079.98</td>\n",
" <td>...</td>\n",
" <td>13.57</td>\n",
" <td>31.96</td>\n",
" <td>2.55</td>\n",
" <td>7.40</td>\n",
" <td>0.15</td>\n",
" <td>660209762.20</td>\n",
" <td>141246.42</td>\n",
" <td>12.48</td>\n",
" <td>25.62</td>\n",
" <td>1894.04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>1.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>...</td>\n",
" <td>7.70</td>\n",
" <td>1.19</td>\n",
" <td>0.10</td>\n",
" <td>53.28</td>\n",
" <td>0.39</td>\n",
" <td>47.00</td>\n",
" <td>-37726.10</td>\n",
" <td>-44.23</td>\n",
" <td>-95.92</td>\n",
" <td>-2142.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>7474.00</td>\n",
" <td>0.00</td>\n",
" <td>0.57</td>\n",
" <td>125.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>2273.89</td>\n",
" <td>0.00</td>\n",
" <td>0.12</td>\n",
" <td>55.47</td>\n",
" <td>...</td>\n",
" <td>22.60</td>\n",
" <td>20.86</td>\n",
" <td>1.30</td>\n",
" <td>69.59</td>\n",
" <td>0.60</td>\n",
" <td>449002.00</td>\n",
" <td>74.80</td>\n",
" <td>1.07</td>\n",
" <td>-1.50</td>\n",
" <td>46.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>65381.00</td>\n",
" <td>4.00</td>\n",
" <td>30.07</td>\n",
" <td>1250.00</td>\n",
" <td>0.00</td>\n",
" <td>0.14</td>\n",
" <td>24535.96</td>\n",
" <td>0.37</td>\n",
" <td>8.25</td>\n",
" <td>358.70</td>\n",
" <td>...</td>\n",
" <td>33.10</td>\n",
" <td>49.84</td>\n",
" <td>2.50</td>\n",
" <td>75.05</td>\n",
" <td>0.74</td>\n",
" <td>5882259.00</td>\n",
" <td>5352.90</td>\n",
" <td>7.96</td>\n",
" <td>6.02</td>\n",
" <td>1021.92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>694038.50</td>\n",
" <td>316.00</td>\n",
" <td>562.29</td>\n",
" <td>11164.75</td>\n",
" <td>3.00</td>\n",
" <td>5.86</td>\n",
" <td>122228.21</td>\n",
" <td>41.74</td>\n",
" <td>92.14</td>\n",
" <td>1298.26</td>\n",
" <td>...</td>\n",
" <td>41.30</td>\n",
" <td>83.24</td>\n",
" <td>4.20</td>\n",
" <td>79.46</td>\n",
" <td>0.83</td>\n",
" <td>28301700.00</td>\n",
" <td>35107.10</td>\n",
" <td>15.37</td>\n",
" <td>16.92</td>\n",
" <td>2615.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>768982331.00</td>\n",
" <td>8401763.00</td>\n",
" <td>6402720.57</td>\n",
" <td>6953730.00</td>\n",
" <td>121590.00</td>\n",
" <td>18214.14</td>\n",
" <td>737554.51</td>\n",
" <td>228872.02</td>\n",
" <td>37241.78</td>\n",
" <td>6501.22</td>\n",
" <td>...</td>\n",
" <td>78.10</td>\n",
" <td>100.00</td>\n",
" <td>13.80</td>\n",
" <td>86.75</td>\n",
" <td>0.96</td>\n",
" <td>7975105024.00</td>\n",
" <td>1281224.50</td>\n",
" <td>76.55</td>\n",
" <td>377.43</td>\n",
" <td>10292.47</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 62 columns</p>\n",
"</div>"
],
"text/plain": [
" total_cases new_cases new_cases_smoothed total_deaths new_deaths \\\n",
"count 293300.00 321633.00 320374.00 272174.00 321702.00 \n",
"mean 6253904.17 10131.10 10167.99 83576.13 91.90 \n",
"std 38541489.37 113417.45 97186.95 429321.51 761.90 \n",
"min 1.00 0.00 0.00 1.00 0.00 \n",
"25% 7474.00 0.00 0.57 125.00 0.00 \n",
"50% 65381.00 4.00 30.07 1250.00 0.00 \n",
"75% 694038.50 316.00 562.29 11164.75 3.00 \n",
"max 768982331.00 8401763.00 6402720.57 6953730.00 121590.00 \n",
"\n",
" new_deaths_smoothed total_cases_per_million new_cases_per_million \\\n",
"count 320472.00 293300.00 321633.00 \n",
"mean 92.24 95300.48 153.11 \n",
"std 597.59 145463.27 1196.21 \n",
"min 0.00 0.00 0.00 \n",
"25% 0.00 2273.89 0.00 \n",
"50% 0.14 24535.96 0.37 \n",
"75% 5.86 122228.21 41.74 \n",
"max 18214.14 737554.51 228872.02 \n",
"\n",
" new_cases_smoothed_per_million total_deaths_per_million ... \\\n",
"count 320374.00 272174.00 ... \n",
"mean 153.68 843.64 ... \n",
"std 616.18 1079.98 ... \n",
"min 0.00 0.00 ... \n",
"25% 0.12 55.47 ... \n",
"50% 8.25 358.70 ... \n",
"75% 92.14 1298.26 ... \n",
"max 37241.78 6501.22 ... \n",
"\n",
" male_smokers handwashing_facilities hospital_beds_per_thousand \\\n",
"count 189702.00 125583.00 226326.00 \n",
"mean 32.91 50.79 3.10 \n",
"std 13.57 31.96 2.55 \n",
"min 7.70 1.19 0.10 \n",
"25% 22.60 20.86 1.30 \n",
"50% 33.10 49.84 2.50 \n",
"75% 41.30 83.24 4.20 \n",
"max 78.10 100.00 13.80 \n",
"\n",
" life_expectancy human_development_index population \\\n",
"count 304234.00 248529.00 330782.00 \n",
"mean 73.72 0.72 128279905.10 \n",
"std 7.40 0.15 660209762.20 \n",
"min 53.28 0.39 47.00 \n",
"25% 69.59 0.60 449002.00 \n",
"50% 75.05 0.74 5882259.00 \n",
"75% 79.46 0.83 28301700.00 \n",
"max 86.75 0.96 7975105024.00 \n",
"\n",
" excess_mortality_cumulative_absolute excess_mortality_cumulative \\\n",
"count 11535.00 11535.00 \n",
"mean 49332.00 9.64 \n",
"std 141246.42 12.48 \n",
"min -37726.10 -44.23 \n",
"25% 74.80 1.07 \n",
"50% 5352.90 7.96 \n",
"75% 35107.10 15.37 \n",
"max 1281224.50 76.55 \n",
"\n",
" excess_mortality excess_mortality_cumulative_per_million \n",
"count 11535.00 11535.00 \n",
"mean 11.82 1591.66 \n",
"std 25.62 1894.04 \n",
"min -95.92 -2142.34 \n",
"25% -1.50 46.90 \n",
"50% 6.02 1021.92 \n",
"75% 16.92 2615.63 \n",
"max 377.43 10292.47 \n",
"\n",
"[8 rows x 62 columns]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"pd.options.display.float_format = ' {:.2f}'.format # set the format for two decimal places\n",
"data.describe() # print the descriptive statistics"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "82663017",
"metadata": {},
"outputs": [],
"source": [
"dates = (\"2023-01-01\", \"2023-08-01\")\n",
"# Convert the date column of the full_df to datetime format\n",
"data['date'] = pd.to_datetime(data['date'])\n",
"# Filter the full_df by the date range using boolean indexing\n",
"df = data[(data['date'] >= dates[0]) & (data['date'] <= dates[1])]"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "0bedb277",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(53733, 67)"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "markdown",
"id": "dbb71f48",
"metadata": {},
"source": [
"## Dataset information"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "97b392bf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 53733 entries, 1094 to 330780\n",
"Data columns (total 67 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 iso_code 53733 non-null object \n",
" 1 continent 51177 non-null object \n",
" 2 location 53733 non-null object \n",
" 3 date 53733 non-null datetime64[ns]\n",
" 4 total_cases 51972 non-null float64 \n",
" 5 new_cases 52338 non-null float64 \n",
" 6 new_cases_smoothed 52338 non-null float64 \n",
" 7 total_deaths 50526 non-null float64 \n",
" 8 new_deaths 52367 non-null float64 \n",
" 9 new_deaths_smoothed 52367 non-null float64 \n",
" 10 total_cases_per_million 51972 non-null float64 \n",
" 11 new_cases_per_million 52338 non-null float64 \n",
" 12 new_cases_smoothed_per_million 52338 non-null float64 \n",
" 13 total_deaths_per_million 50526 non-null float64 \n",
" 14 new_deaths_per_million 52367 non-null float64 \n",
" 15 new_deaths_smoothed_per_million 52367 non-null float64 \n",
" 16 reproduction_rate 390 non-null float64 \n",
" 17 icu_patients 4181 non-null float64 \n",
" 18 icu_patients_per_million 4181 non-null float64 \n",
" 19 hosp_patients 4625 non-null float64 \n",
" 20 hosp_patients_per_million 4625 non-null float64 \n",
" 21 weekly_icu_admissions 1622 non-null float64 \n",
" 22 weekly_icu_admissions_per_million 1622 non-null float64 \n",
" 23 weekly_hosp_admissions 2961 non-null float64 \n",
" 24 weekly_hosp_admissions_per_million 2961 non-null float64 \n",
" 25 total_tests 0 non-null float64 \n",
" 26 new_tests 0 non-null float64 \n",
" 27 total_tests_per_thousand 0 non-null float64 \n",
" 28 new_tests_per_thousand 0 non-null float64 \n",
" 29 new_tests_smoothed 0 non-null float64 \n",
" 30 new_tests_smoothed_per_thousand 0 non-null float64 \n",
" 31 positive_rate 0 non-null float64 \n",
" 32 tests_per_case 0 non-null float64 \n",
" 33 tests_units 0 non-null object \n",
" 34 total_vaccinations 8646 non-null float64 \n",
" 35 people_vaccinated 8490 non-null float64 \n",
" 36 people_fully_vaccinated 8475 non-null float64 \n",
" 37 total_boosters 7806 non-null float64 \n",
" 38 new_vaccinations 7075 non-null float64 \n",
" 39 new_vaccinations_smoothed 24313 non-null float64 \n",
" 40 total_vaccinations_per_hundred 8646 non-null float64 \n",
" 41 people_vaccinated_per_hundred 8490 non-null float64 \n",
" 42 people_fully_vaccinated_per_hundred 8475 non-null float64 \n",
" 43 total_boosters_per_hundred 7806 non-null float64 \n",
" 44 new_vaccinations_smoothed_per_million 24313 non-null float64 \n",
" 45 new_people_vaccinated_smoothed 24502 non-null float64 \n",
" 46 new_people_vaccinated_smoothed_per_hundred 24502 non-null float64 \n",
" 47 stringency_index 0 non-null float64 \n",
" 48 population_density 45681 non-null float64 \n",
" 49 median_age 42470 non-null float64 \n",
" 50 aged_65_older 40995 non-null float64 \n",
" 51 aged_70_older 42044 non-null float64 \n",
" 52 gdp_per_capita 41634 non-null float64 \n",
" 53 extreme_poverty 26838 non-null float64 \n",
" 54 cardiovasc_death_rate 41732 non-null float64 \n",
" 55 diabetes_prevalence 43874 non-null float64 \n",
" 56 female_smokers 31311 non-null float64 \n",
" 57 male_smokers 30885 non-null float64 \n",
" 58 handwashing_facilities 20448 non-null float64 \n",
" 59 hospital_beds_per_thousand 36849 non-null float64 \n",
" 60 life_expectancy 49499 non-null float64 \n",
" 61 human_development_index 40466 non-null float64 \n",
" 62 population 53733 non-null float64 \n",
" 63 excess_mortality_cumulative_absolute 1327 non-null float64 \n",
" 64 excess_mortality_cumulative 1327 non-null float64 \n",
" 65 excess_mortality 1327 non-null float64 \n",
" 66 excess_mortality_cumulative_per_million 1327 non-null float64 \n",
"dtypes: datetime64[ns](1), float64(62), object(4)\n",
"memory usage: 27.9+ MB\n"
]
}
],
"source": [
"df.info()"
]
},
{
"cell_type": "markdown",
"id": "99fb3e47",
"metadata": {},
"source": [
"## Checking missing values"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "5a8c5c5a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: >"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 2500x1000 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Plot the missing values matrix\n",
"msno.matrix(data)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "d37cbb66",
"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>Missing Data Ratio (%)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>iso_code</th>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>continent</th>\n",
" <td>4.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>location</th>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>date</th>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_cases</th>\n",
" <td>11.33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_cases</th>\n",
" <td>2.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_cases_smoothed</th>\n",
" <td>3.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_deaths</th>\n",
" <td>17.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_deaths</th>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_deaths_smoothed</th>\n",
" <td>3.12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_cases_per_million</th>\n",
" <td>11.33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_cases_per_million</th>\n",
" <td>2.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_cases_smoothed_per_million</th>\n",
" <td>3.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_deaths_per_million</th>\n",
" <td>17.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_deaths_per_million</th>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_deaths_smoothed_per_million</th>\n",
" <td>3.12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>reproduction_rate</th>\n",
" <td>44.13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>icu_patients</th>\n",
" <td>88.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>icu_patients_per_million</th>\n",
" <td>88.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>hosp_patients</th>\n",
" <td>88.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>hosp_patients_per_million</th>\n",
" <td>88.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>weekly_icu_admissions</th>\n",
" <td>97.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>weekly_icu_admissions_per_million</th>\n",
" <td>97.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>weekly_hosp_admissions</th>\n",
" <td>93.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>weekly_hosp_admissions_per_million</th>\n",
" <td>93.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_tests</th>\n",
" <td>76.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_tests</th>\n",
" <td>77.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_tests_per_thousand</th>\n",
" <td>76.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_tests_per_thousand</th>\n",
" <td>77.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_tests_smoothed</th>\n",
" <td>68.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_tests_smoothed_per_thousand</th>\n",
" <td>68.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>positive_rate</th>\n",
" <td>71.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>tests_per_case</th>\n",
" <td>71.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>tests_units</th>\n",
" <td>67.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_vaccinations</th>\n",
" <td>76.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>people_vaccinated</th>\n",
" <td>77.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>people_fully_vaccinated</th>\n",
" <td>78.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_boosters</th>\n",
" <td>86.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_vaccinations</th>\n",
" <td>80.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_vaccinations_smoothed</th>\n",
" <td>47.11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_vaccinations_per_hundred</th>\n",
" <td>76.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>people_vaccinated_per_hundred</th>\n",
" <td>77.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>people_fully_vaccinated_per_hundred</th>\n",
" <td>78.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>total_boosters_per_hundred</th>\n",
" <td>86.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_vaccinations_smoothed_per_million</th>\n",
" <td>47.11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_people_vaccinated_smoothed</th>\n",
" <td>47.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>new_people_vaccinated_smoothed_per_hundred</th>\n",
" <td>47.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>stringency_index</th>\n",
" <td>40.25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>population_density</th>\n",
" <td>15.13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>median_age</th>\n",
" <td>21.07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>aged_65_older</th>\n",
" <td>23.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>aged_70_older</th>\n",
" <td>21.87</td>\n",
" </tr>\n",
" <tr>\n",
" <th>gdp_per_capita</th>\n",
" <td>22.65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>extreme_poverty</th>\n",
" <td>50.17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>cardiovasc_death_rate</th>\n",
" <td>22.49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>diabetes_prevalence</th>\n",
" <td>18.54</td>\n",
" </tr>\n",
" <tr>\n",
" <th>female_smokers</th>\n",
" <td>41.86</td>\n",
" </tr>\n",
" <tr>\n",
" <th>male_smokers</th>\n",
" <td>42.65</td>\n",
" </tr>\n",
" <tr>\n",
" <th>handwashing_facilities</th>\n",
" <td>62.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>hospital_beds_per_thousand</th>\n",
" <td>31.58</td>\n",
" </tr>\n",
" <tr>\n",
" <th>life_expectancy</th>\n",
" <td>8.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>human_development_index</th>\n",
" <td>24.87</td>\n",
" </tr>\n",
" <tr>\n",
" <th>population</th>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>excess_mortality_cumulative_absolute</th>\n",
" <td>96.51</td>\n",
" </tr>\n",
" <tr>\n",
" <th>excess_mortality_cumulative</th>\n",
" <td>96.51</td>\n",
" </tr>\n",
" <tr>\n",
" <th>excess_mortality</th>\n",
" <td>96.51</td>\n",
" </tr>\n",
" <tr>\n",
" <th>excess_mortality_cumulative_per_million</th>\n",
" <td>96.51</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Missing Data Ratio (%)\n",
"iso_code 0.00\n",
"continent 4.75\n",
"location 0.00\n",
"date 0.00\n",
"total_cases 11.33\n",
"new_cases 2.77\n",
"new_cases_smoothed 3.15\n",
"total_deaths 17.72\n",
"new_deaths 2.75\n",
"new_deaths_smoothed 3.12\n",
"total_cases_per_million 11.33\n",
"new_cases_per_million 2.77\n",
"new_cases_smoothed_per_million 3.15\n",
"total_deaths_per_million 17.72\n",
"new_deaths_per_million 2.75\n",
"new_deaths_smoothed_per_million 3.12\n",
"reproduction_rate 44.13\n",
"icu_patients 88.80\n",
"icu_patients_per_million 88.80\n",
"hosp_patients 88.50\n",
"hosp_patients_per_million 88.50\n",
"weekly_icu_admissions 97.01\n",
"weekly_icu_admissions_per_million 97.01\n",
"weekly_hosp_admissions 93.15\n",
"weekly_hosp_admissions_per_million 93.15\n",
"total_tests 76.00\n",
"new_tests 77.20\n",
"total_tests_per_thousand 76.00\n",
"new_tests_per_thousand 77.20\n",
"new_tests_smoothed 68.57\n",
"new_tests_smoothed_per_thousand 68.57\n",
"positive_rate 71.00\n",
"tests_per_case 71.48\n",
"tests_units 67.72\n",
"total_vaccinations 76.59\n",
"people_vaccinated 77.59\n",
"people_fully_vaccinated 78.63\n",
"total_boosters 86.15\n",
"new_vaccinations 80.73\n",
"new_vaccinations_smoothed 47.11\n",
"total_vaccinations_per_hundred 76.59\n",
"people_vaccinated_per_hundred 77.59\n",
"people_fully_vaccinated_per_hundred 78.63\n",
"total_boosters_per_hundred 86.15\n",
"new_vaccinations_smoothed_per_million 47.11\n",
"new_people_vaccinated_smoothed 47.10\n",
"new_people_vaccinated_smoothed_per_hundred 47.10\n",
"stringency_index 40.25\n",
"population_density 15.13\n",
"median_age 21.07\n",
"aged_65_older 23.83\n",
"aged_70_older 21.87\n",
"gdp_per_capita 22.65\n",
"extreme_poverty 50.17\n",
"cardiovasc_death_rate 22.49\n",
"diabetes_prevalence 18.54\n",
"female_smokers 41.86\n",
"male_smokers 42.65\n",
"handwashing_facilities 62.03\n",
"hospital_beds_per_thousand 31.58\n",
"life_expectancy 8.03\n",
"human_development_index 24.87\n",
"population 0.00\n",
"excess_mortality_cumulative_absolute 96.51\n",
"excess_mortality_cumulative 96.51\n",
"excess_mortality 96.51\n",
"excess_mortality_cumulative_per_million 96.51"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Import pandas as pd\n",
"import pandas as pd\n",
"\n",
"# Import display from IPython.display\n",
"from IPython.display import display\n",
"\n",
"# Calculate the missing data ratio for each column as percentages\n",
"missing_data_ratio = data.isnull().mean() * 100\n",
"\n",
"# Convert the Series to a DataFrame for better display\n",
"missing_data_df = pd.DataFrame({'Missing Data Ratio (%)': missing_data_ratio})\n",
"\n",
"# Display the missing data ratio for each column as percentages in a scrollable DataFrame\n",
"with pd.option_context('display.max_rows', None):\n",
" display(missing_data_df)"
]
},
{
"cell_type": "markdown",
"id": "394bdfc0",
"metadata": {},
"source": [
"## Checking outliers"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "9175462b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Outliers:\n"
]
},
{
"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>iso_code</th>\n",
" <th>continent</th>\n",
" <th>location</th>\n",
" <th>date</th>\n",
" <th>total_cases</th>\n",
" <th>new_cases</th>\n",
" <th>new_cases_smoothed</th>\n",
" <th>total_deaths</th>\n",
" <th>new_deaths</th>\n",
" <th>new_deaths_smoothed</th>\n",
" <th>...</th>\n",
" <th>male_smokers</th>\n",
" <th>handwashing_facilities</th>\n",
" <th>hospital_beds_per_thousand</th>\n",
" <th>life_expectancy</th>\n",
" <th>human_development_index</th>\n",
" <th>population</th>\n",
" <th>excess_mortality_cumulative_absolute</th>\n",
" <th>excess_mortality_cumulative</th>\n",
" <th>excess_mortality</th>\n",
" <th>excess_mortality_cumulative_per_million</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>16498</th>\n",
" <td>OWID_ASI</td>\n",
" <td>NaN</td>\n",
" <td>Asia</td>\n",
" <td>2022-03-08</td>\n",
" <td>122507617.00</td>\n",
" <td>791293.00</td>\n",
" <td>706920.57</td>\n",
" <td>1365917.00</td>\n",
" <td>1917.00</td>\n",
" <td>1951.86</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4721383370.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16499</th>\n",
" <td>OWID_ASI</td>\n",
" <td>NaN</td>\n",
" <td>Asia</td>\n",
" <td>2022-03-09</td>\n",
" <td>123354783.00</td>\n",
" <td>847166.00</td>\n",
" <td>727234.14</td>\n",
" <td>1367885.00</td>\n",
" <td>1968.00</td>\n",
" <td>1926.00</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4721383370.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16500</th>\n",
" <td>OWID_ASI</td>\n",
" <td>NaN</td>\n",
" <td>Asia</td>\n",
" <td>2022-03-10</td>\n",
" <td>124101007.00</td>\n",
" <td>746224.00</td>\n",
" <td>721573.14</td>\n",
" <td>1369710.00</td>\n",
" <td>1825.00</td>\n",
" <td>1916.57</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4721383370.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16501</th>\n",
" <td>OWID_ASI</td>\n",
" <td>NaN</td>\n",
" <td>Asia</td>\n",
" <td>2022-03-11</td>\n",
" <td>124898209.00</td>\n",
" <td>797202.00</td>\n",
" <td>730206.43</td>\n",
" <td>1371566.00</td>\n",
" <td>1856.00</td>\n",
" <td>1864.14</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4721383370.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16502</th>\n",
" <td>OWID_ASI</td>\n",
" <td>NaN</td>\n",
" <td>Asia</td>\n",
" <td>2022-03-12</td>\n",
" <td>125930442.00</td>\n",
" <td>1032233.00</td>\n",
" <td>775388.00</td>\n",
" <td>1373481.00</td>\n",
" <td>1915.00</td>\n",
" <td>1848.57</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4721383370.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>326850</th>\n",
" <td>OWID_WRL</td>\n",
" <td>NaN</td>\n",
" <td>World</td>\n",
" <td>2023-07-29</td>\n",
" <td>768632837.00</td>\n",
" <td>694.00</td>\n",
" <td>46823.57</td>\n",
" <td>6953094.00</td>\n",
" <td>11.00</td>\n",
" <td>75.00</td>\n",
" <td>...</td>\n",
" <td>34.63</td>\n",
" <td>60.13</td>\n",
" <td>2.71</td>\n",
" <td>72.58</td>\n",
" <td>0.74</td>\n",
" <td>7975105024.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>326851</th>\n",
" <td>OWID_WRL</td>\n",
" <td>NaN</td>\n",
" <td>World</td>\n",
" <td>2023-07-30</td>\n",
" <td>768654204.00</td>\n",
" <td>21367.00</td>\n",
" <td>45918.43</td>\n",
" <td>6953470.00</td>\n",
" <td>376.00</td>\n",
" <td>87.00</td>\n",
" <td>...</td>\n",
" <td>34.63</td>\n",
" <td>60.13</td>\n",
" <td>2.71</td>\n",
" <td>72.58</td>\n",
" <td>0.74</td>\n",
" <td>7975105024.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>326852</th>\n",
" <td>OWID_WRL</td>\n",
" <td>NaN</td>\n",
" <td>World</td>\n",
" <td>2023-07-31</td>\n",
" <td>768978837.00</td>\n",
" <td>324633.00</td>\n",
" <td>50862.86</td>\n",
" <td>6953676.00</td>\n",
" <td>206.00</td>\n",
" <td>97.29</td>\n",
" <td>...</td>\n",
" <td>34.63</td>\n",
" <td>60.13</td>\n",
" <td>2.71</td>\n",
" <td>72.58</td>\n",
" <td>0.74</td>\n",
" <td>7975105024.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>326853</th>\n",
" <td>OWID_WRL</td>\n",
" <td>NaN</td>\n",
" <td>World</td>\n",
" <td>2023-08-01</td>\n",
" <td>768982331.00</td>\n",
" <td>3494.00</td>\n",
" <td>50703.29</td>\n",
" <td>6953730.00</td>\n",
" <td>54.00</td>\n",
" <td>97.00</td>\n",
" <td>...</td>\n",
" <td>34.63</td>\n",
" <td>60.13</td>\n",
" <td>2.71</td>\n",
" <td>72.58</td>\n",
" <td>0.74</td>\n",
" <td>7975105024.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>326854</th>\n",
" <td>OWID_WRL</td>\n",
" <td>NaN</td>\n",
" <td>World</td>\n",
" <td>2023-08-02</td>\n",
" <td>768982331.00</td>\n",
" <td>0.00</td>\n",
" <td>50420.57</td>\n",
" <td>6953730.00</td>\n",
" <td>0.00</td>\n",
" <td>96.29</td>\n",
" <td>...</td>\n",
" <td>34.63</td>\n",
" <td>60.13</td>\n",
" <td>2.71</td>\n",
" <td>72.58</td>\n",
" <td>0.74</td>\n",
" <td>7975105024.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3675 rows × 67 columns</p>\n",
"</div>"
],
"text/plain": [
" iso_code continent location date total_cases new_cases \\\n",
"16498 OWID_ASI NaN Asia 2022-03-08 122507617.00 791293.00 \n",
"16499 OWID_ASI NaN Asia 2022-03-09 123354783.00 847166.00 \n",
"16500 OWID_ASI NaN Asia 2022-03-10 124101007.00 746224.00 \n",
"16501 OWID_ASI NaN Asia 2022-03-11 124898209.00 797202.00 \n",
"16502 OWID_ASI NaN Asia 2022-03-12 125930442.00 1032233.00 \n",
"... ... ... ... ... ... ... \n",
"326850 OWID_WRL NaN World 2023-07-29 768632837.00 694.00 \n",
"326851 OWID_WRL NaN World 2023-07-30 768654204.00 21367.00 \n",
"326852 OWID_WRL NaN World 2023-07-31 768978837.00 324633.00 \n",
"326853 OWID_WRL NaN World 2023-08-01 768982331.00 3494.00 \n",
"326854 OWID_WRL NaN World 2023-08-02 768982331.00 0.00 \n",
"\n",
" new_cases_smoothed total_deaths new_deaths new_deaths_smoothed \\\n",
"16498 706920.57 1365917.00 1917.00 1951.86 \n",
"16499 727234.14 1367885.00 1968.00 1926.00 \n",
"16500 721573.14 1369710.00 1825.00 1916.57 \n",
"16501 730206.43 1371566.00 1856.00 1864.14 \n",
"16502 775388.00 1373481.00 1915.00 1848.57 \n",
"... ... ... ... ... \n",
"326850 46823.57 6953094.00 11.00 75.00 \n",
"326851 45918.43 6953470.00 376.00 87.00 \n",
"326852 50862.86 6953676.00 206.00 97.29 \n",
"326853 50703.29 6953730.00 54.00 97.00 \n",
"326854 50420.57 6953730.00 0.00 96.29 \n",
"\n",
" ... male_smokers handwashing_facilities hospital_beds_per_thousand \\\n",
"16498 ... NaN NaN NaN \n",
"16499 ... NaN NaN NaN \n",
"16500 ... NaN NaN NaN \n",
"16501 ... NaN NaN NaN \n",
"16502 ... NaN NaN NaN \n",
"... ... ... ... ... \n",
"326850 ... 34.63 60.13 2.71 \n",
"326851 ... 34.63 60.13 2.71 \n",
"326852 ... 34.63 60.13 2.71 \n",
"326853 ... 34.63 60.13 2.71 \n",
"326854 ... 34.63 60.13 2.71 \n",
"\n",
" life_expectancy human_development_index population \\\n",
"16498 NaN NaN 4721383370.00 \n",
"16499 NaN NaN 4721383370.00 \n",
"16500 NaN NaN 4721383370.00 \n",
"16501 NaN NaN 4721383370.00 \n",
"16502 NaN NaN 4721383370.00 \n",
"... ... ... ... \n",
"326850 72.58 0.74 7975105024.00 \n",
"326851 72.58 0.74 7975105024.00 \n",
"326852 72.58 0.74 7975105024.00 \n",
"326853 72.58 0.74 7975105024.00 \n",
"326854 72.58 0.74 7975105024.00 \n",
"\n",
" excess_mortality_cumulative_absolute excess_mortality_cumulative \\\n",
"16498 NaN NaN \n",
"16499 NaN NaN \n",
"16500 NaN NaN \n",
"16501 NaN NaN \n",
"16502 NaN NaN \n",
"... ... ... \n",
"326850 NaN NaN \n",
"326851 NaN NaN \n",
"326852 NaN NaN \n",
"326853 NaN NaN \n",
"326854 NaN NaN \n",
"\n",
" excess_mortality excess_mortality_cumulative_per_million \n",
"16498 NaN NaN \n",
"16499 NaN NaN \n",
"16500 NaN NaN \n",
"16501 NaN NaN \n",
"16502 NaN NaN \n",
"... ... ... \n",
"326850 NaN NaN \n",
"326851 NaN NaN \n",
"326852 NaN NaN \n",
"326853 NaN NaN \n",
"326854 NaN NaN \n",
"\n",
"[3675 rows x 67 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Load your dataset (assuming you already have 'data' DataFrame)\n",
"df = data.copy()\n",
"\n",
"# Define the column to check for outliers\n",
"column_name = 'total_cases'\n",
"column_data = df[column_name]\n",
"\n",
"# Calculate Z-scores for the 'total_cases' column\n",
"z_scores = (column_data - column_data.mean()) / column_data.std()\n",
"\n",
"# Define the threshold for Z-score to identify outliers\n",
"threshold = 3\n",
"\n",
"# Identify outliers based on the absolute Z-scores exceeding the threshold\n",
"outliers = df[abs(z_scores) > threshold]\n",
"\n",
"# Print the outliers\n",
"print(\"Outliers:\")\n",
"display(outliers)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2d409dd5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}