"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "032d5c8f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Data As Of Start Date End Date Group Year Month State \\\n",
"0 09/24/2023 01/01/2020 09/23/2023 By Total NaN NaN United States \n",
"1 09/24/2023 01/01/2020 09/23/2023 By Total NaN NaN United States \n",
"2 09/24/2023 01/01/2020 09/23/2023 By Total NaN NaN United States \n",
"3 09/24/2023 01/01/2020 09/23/2023 By Total NaN NaN United States \n",
"4 09/24/2023 01/01/2020 09/23/2023 By Total NaN NaN United States \n",
"\n",
" Condition Group Condition ICD10_codes Age Group \\\n",
"0 Respiratory diseases Influenza and pneumonia J09-J18 0-24 \n",
"1 Respiratory diseases Influenza and pneumonia J09-J18 25-34 \n",
"2 Respiratory diseases Influenza and pneumonia J09-J18 35-44 \n",
"3 Respiratory diseases Influenza and pneumonia J09-J18 45-54 \n",
"4 Respiratory diseases Influenza and pneumonia J09-J18 55-64 \n",
"\n",
" COVID-19 Deaths Number of Mentions Flag \n",
"0 1569.0 1647.0 NaN \n",
"1 5804.0 6029.0 NaN \n",
"2 15080.0 15699.0 NaN \n",
"3 37414.0 38878.0 NaN \n",
"4 82668.0 85708.0 NaN \n"
]
}
],
"source": [
"import pandas as pd\n",
"file_path_1 = 'Conditions_Contributing_to_COVID-19_Deaths__by_State_and_Age__Provisional_2020-2023.csv'\n",
"data_1 = pd.read_csv(file_path_1)\n",
"print(data_1.head())"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a90d5564",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((621000, 14),\n",
" Data As Of Start Date End Date Group Year \\\n",
" count 621000 621000 621000 621000 608580.000000 \n",
" unique 1 45 45 3 NaN \n",
" top 09/24/2023 01/01/2020 09/23/2023 By Month NaN \n",
" freq 621000 37260 37260 558900 NaN \n",
" mean NaN NaN NaN NaN 2021.408163 \n",
" std NaN NaN NaN NaN 1.086436 \n",
" min NaN NaN NaN NaN 2020.000000 \n",
" 25% NaN NaN NaN NaN 2020.000000 \n",
" 50% NaN NaN NaN NaN 2021.000000 \n",
" 75% NaN NaN NaN NaN 2022.000000 \n",
" max NaN NaN NaN NaN 2023.000000 \n",
" \n",
" Month State Condition Group \\\n",
" count 558900.000000 621000 621000 \n",
" unique NaN 54 12 \n",
" top NaN United States Circulatory diseases \n",
" freq NaN 11500 189000 \n",
" mean 6.200000 NaN NaN \n",
" std 3.350625 NaN NaN \n",
" min 1.000000 NaN NaN \n",
" 25% 3.000000 NaN NaN \n",
" 50% 6.000000 NaN NaN \n",
" 75% 9.000000 NaN NaN \n",
" max 12.000000 NaN NaN \n",
" \n",
" Condition ICD10_codes Age Group COVID-19 Deaths \\\n",
" count 621000 621000 621000 4.375510e+05 \n",
" unique 23 23 10 NaN \n",
" top Influenza and pneumonia J09-J18 0-24 NaN \n",
" freq 27000 27000 62100 NaN \n",
" mean NaN NaN NaN 1.201179e+02 \n",
" std NaN NaN NaN 2.980201e+03 \n",
" min NaN NaN NaN 0.000000e+00 \n",
" 25% NaN NaN NaN 0.000000e+00 \n",
" 50% NaN NaN NaN 0.000000e+00 \n",
" 75% NaN NaN NaN 1.800000e+01 \n",
" max NaN NaN NaN 1.146242e+06 \n",
" \n",
" Number of Mentions Flag \n",
" count 4.434230e+05 183449 \n",
" unique NaN 1 \n",
" top NaN One or more data cells have counts between 1-9... \n",
" freq NaN 183449 \n",
" mean 1.293348e+02 NaN \n",
" std 3.203936e+03 NaN \n",
" min 0.000000e+00 NaN \n",
" 25% 0.000000e+00 NaN \n",
" 50% 0.000000e+00 NaN \n",
" 75% 1.900000e+01 NaN \n",
" max 1.146242e+06 NaN ,\n",
" Data As Of Start Date End Date Group Year Month \\\n",
" 620995 09/24/2023 05/01/2023 05/31/2023 By Month 2023.0 5.0 \n",
" 620996 09/24/2023 06/01/2023 06/30/2023 By Month 2023.0 6.0 \n",
" 620997 09/24/2023 07/01/2023 07/31/2023 By Month 2023.0 7.0 \n",
" 620998 09/24/2023 08/01/2023 08/31/2023 By Month 2023.0 8.0 \n",
" 620999 09/24/2023 09/01/2023 09/23/2023 By Month 2023.0 9.0 \n",
" \n",
" State Condition Group Condition ICD10_codes Age Group \\\n",
" 620995 Puerto Rico COVID-19 COVID-19 U071 All Ages \n",
" 620996 Puerto Rico COVID-19 COVID-19 U071 All Ages \n",
" 620997 Puerto Rico COVID-19 COVID-19 U071 All Ages \n",
" 620998 Puerto Rico COVID-19 COVID-19 U071 All Ages \n",
" 620999 Puerto Rico COVID-19 COVID-19 U071 All Ages \n",
" \n",
" COVID-19 Deaths Number of Mentions Flag \n",
" 620995 67.0 67.0 NaN \n",
" 620996 122.0 122.0 NaN \n",
" 620997 114.0 114.0 NaN \n",
" 620998 78.0 78.0 NaN \n",
" 620999 36.0 36.0 NaN ,\n",
" Data As Of object\n",
" Start Date object\n",
" End Date object\n",
" Group object\n",
" Year float64\n",
" Month float64\n",
" State object\n",
" Condition Group object\n",
" Condition object\n",
" ICD10_codes object\n",
" Age Group object\n",
" COVID-19 Deaths float64\n",
" Number of Mentions float64\n",
" Flag object\n",
" dtype: object)"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_1_shape = data_1.shape\n",
"\n",
"# Descriptive statistics for all columns\n",
"data_1_describe = data_1.describe(include='all')\n",
"\n",
"# Display the last few rows of the DataFrame\n",
"data_1_tail = data_1.tail()\n",
"\n",
"# Display the data types of each column\n",
"data_1_dtypes = data_1.dtypes\n",
"\n",
"data_1_shape, data_1_describe, data_1_tail, data_1_dtypes"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a33437ba",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 3,
"id": "6016716c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Data As Of Start Date End Date Group Year Month \\\n",
"0 2023-09-24 2020-01-01 2023-09-23 By Total NaN NaN \n",
"1 2023-09-24 2020-01-01 2023-09-23 By Total NaN NaN \n",
"2 2023-09-24 2020-01-01 2023-09-23 By Total NaN NaN \n",
"3 2023-09-24 2020-01-01 2023-09-23 By Total NaN NaN \n",
"4 2023-09-24 2020-01-01 2023-09-23 By Total NaN NaN \n",
"... ... ... ... ... ... ... \n",
"620995 2023-09-24 2023-05-01 2023-05-31 By Month 2023.0 5.0 \n",
"620996 2023-09-24 2023-06-01 2023-06-30 By Month 2023.0 6.0 \n",
"620997 2023-09-24 2023-07-01 2023-07-31 By Month 2023.0 7.0 \n",
"620998 2023-09-24 2023-08-01 2023-08-31 By Month 2023.0 8.0 \n",
"620999 2023-09-24 2023-09-01 2023-09-23 By Month 2023.0 9.0 \n",
"\n",
" State Condition Group Condition \\\n",
"0 United States Respiratory diseases Influenza and pneumonia \n",
"1 United States Respiratory diseases Influenza and pneumonia \n",
"2 United States Respiratory diseases Influenza and pneumonia \n",
"3 United States Respiratory diseases Influenza and pneumonia \n",
"4 United States Respiratory diseases Influenza and pneumonia \n",
"... ... ... ... \n",
"620995 Puerto Rico COVID-19 COVID-19 \n",
"620996 Puerto Rico COVID-19 COVID-19 \n",
"620997 Puerto Rico COVID-19 COVID-19 \n",
"620998 Puerto Rico COVID-19 COVID-19 \n",
"620999 Puerto Rico COVID-19 COVID-19 \n",
"\n",
" ICD10_codes Age Group COVID-19 Deaths Number of Mentions Flag \n",
"0 J09-J18 0-24 1569.0 1647.0 NaN \n",
"1 J09-J18 25-34 5804.0 6029.0 NaN \n",
"2 J09-J18 35-44 15080.0 15699.0 NaN \n",
"3 J09-J18 45-54 37414.0 38878.0 NaN \n",
"4 J09-J18 55-64 82668.0 85708.0 NaN \n",
"... ... ... ... ... ... \n",
"620995 U071 All Ages 67.0 67.0 NaN \n",
"620996 U071 All Ages 122.0 122.0 NaN \n",
"620997 U071 All Ages 114.0 114.0 NaN \n",
"620998 U071 All Ages 78.0 78.0 NaN \n",
"620999 U071 All Ages 36.0 36.0 NaN \n",
"\n",
"[621000 rows x 14 columns]\n"
]
}
],
"source": [
"data_1 = pd.DataFrame(data_1)\n",
"\n",
"# Convert dates to datetime\n",
"data_1['Data As Of'] = pd.to_datetime(data_1['Data As Of'])\n",
"data_1['Start Date'] = pd.to_datetime(data_1['Start Date'])\n",
"data_1 ['End Date'] = pd.to_datetime(data_1['End Date'])\n",
"\n",
"# Display the DataFrame\n",
"print(data_1)\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "08b0192f",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"