yeger/Master-DataScience-Notes
1
0
Fork 0
mirror of https://github.com/Andreaierardi/Master-DataScience-Notes.git synced 2024-11-11 06:19:32 +01:00
Code Issues Projects Releases Wiki Activity
c2c84ccea9
Master-DataScience-Notes/1year/2trimester/Coding for Data Science - Python language/Python/Examples/Untitled.ipynb
Andreaierardi 9a8b7bcc1c up
2021-01-24 14:04:49 +01:00

610 lines
18 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3058: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" interactivity=interactivity, compiler=compiler, result=result)\n"
]
}
],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from datetime import date\n",
"\n",
"## Real data: begins with \"R\"\n",
"# Real Deaths: RD\n",
"RD = pd.read_csv(\"https://raw.githubusercontent.com/reichlab/covid19-forecast-hub/master/data-truth/truth-Cumulative%20Deaths.csv\")\n",
"# Real Cases: RC\n",
"RC = pd.read_csv(\"https://raw.githubusercontent.com/reichlab/covid19-forecast-hub/master/data-truth/truth-Cumulative%20Cases.csv\")\n",
"\n",
"Rstates = RD.location_name.unique()\n",
"\n",
"# Real Series getter\n",
"def getRS(type, state, aggregateOn = 5):\n",
" \"\"\"Gets the real cases or deaths series by state\n",
"\n",
" Parameters\n",
" ----------\n",
" type : str\n",
" 'C' for cumulative cases. \n",
" 'D' for cumulative deaths.\n",
" state : str\n",
" The state where deaths were recorded\n",
" aggregateOn : int or bool\n",
" The weekday to aggregate the observations on.\n",
" 0 is Monday, 6 is Sunday.\n",
" Set to false to prevent aggregation.\n",
"\n",
" Returns\n",
" -------\n",
" pandas.Series : the series of real cases or deaths of the specified state. Indexes are of class pandas.DatetimeIndex.\n",
" \"\"\"\n",
" if(type == 'C'):\n",
" out = pd.Series(RC[RC['location_name'] == state].iloc[:,3].values,\n",
" index = pd.to_datetime(RC[RC['location_name'] == state].iloc[:,0].values, format=\"%Y-%m-%d\"),\n",
" name = state + \": Cumulative cases\")\n",
" elif(type == 'D'):\n",
" out = pd.Series(RD[RD['location_name'] == state].iloc[:,3].values,\n",
" index = pd.to_datetime(RD[RD['location_name'] == state].iloc[:,0].values, format=\"%Y-%m-%d\"),\n",
" name = state + \": Cumulative deaths\"\n",
" )\n",
" if(aggregateOn is not False):\n",
" out = out[out.index.weekday == aggregateOn]\n",
"\n",
" return(out)\n",
"\n",
"# Example: getRS('D',Rstates[1])\n",
"\n",
"# # shift series to first non-zero occurence\n",
"# daily_s = daily_s[daily_s>0]\n",
"# # switch aggregation range to weekly (every Saturday)\n",
"# D = daily_s[daily_s.index.weekday == 5]\n",
"\n",
"\n",
"## Forecast data: begins with \"F\"\n",
"# Forecasted cases: FC\n",
"FC = pd.read_csv(\"https://www.cdc.gov/coronavirus/2019-ncov/downloads/cases-updates/2020-10-19-all-forecasted-cases-model-data.csv\")\n",
"# Forecasted deaths: FD\n",
"FD = pd.read_csv('https://www.cdc.gov/coronavirus/2019-ncov/covid-data/files/2020-10-19-model-data.csv')\n",
"\n",
"Fmodels = FD.model.unique()\n",
"Fstates = FD.location_name.unique()\n",
"\n",
"# Forecast Series getter\n",
"def getFS(type, model, state, Fdate):\n",
" \"\"\"Gets the forecasted deaths series by model, state and forecast date\n",
"\n",
" Parameters\n",
" ----------\n",
" type : str\n",
" 'C' for cumulative cases. \n",
" 'D' for cumulative deaths.\n",
" model : str\n",
" The model of the forecast\n",
" state : str\n",
" The target state of the forecast\n",
" Fdate : str or datetime\n",
" The date when the forecast was performed. If a string, provide the format '%Y-%m-%d'.\n",
"\n",
" Returns\n",
" -------\n",
" pandas.DataFrame\n",
" a data frame containing 5 series:\n",
" - point series\n",
" - 2.5% quantile\n",
" - 25% quantile\n",
" - 75% quantile\n",
" - 97.5% quantile\n",
" Indexes are of class pandas.DatetimeIndex.\n",
" \"\"\"\n",
" if(type == 'C'):\n",
" out = FC[(FC.model == model) & (FC.location_name == state) & (FC.forecast_date == Fdate)] \n",
" elif(type == 'D'):\n",
" out = FD[(FD.model == model) & (FD.location_name == state) & (FD.forecast_date == Fdate) & FD.target.apply(str.endswith, args=('cum death',0))]\n",
" else:\n",
" return None\n",
" if( out.empty ):\n",
" return None\n",
" out = pd.DataFrame(out.iloc[:,-5:].values,\n",
" columns = out.columns[-5:],\n",
" index = pd.to_datetime(out.iloc[:,3], format=\"%Y-%m-%d\")\n",
" )\n",
" \n",
" return out\n",
" \n",
"# Example: getFS('C', Fmodels[1], Fstates[1], FD.forecast_date[1])\n",
"\n",
"\n",
"\n",
"\n",
"# prova1 = pd.ExcelFile('Matlab to python/data_models-Florida.xlsx')\n",
"\n",
"# prova1.sheet_names\n",
"\n",
"# prova2 = prova1.parse('Ensamble')\n",
"# prova2\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['Alabama', 'Alaska', 'American Samoa', ..., 'Uinta County',\n",
" 'Washakie County', 'Weston County'], dtype=object)"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2020-01-25 0\n",
"2020-02-01 0\n",
"2020-02-08 0\n",
"2020-02-15 0\n",
"2020-02-22 0\n",
"2020-02-29 0\n",
"2020-03-07 0\n",
"2020-03-14 0\n",
"2020-03-21 0\n",
"2020-03-28 2\n",
"2020-04-04 5\n",
"2020-04-11 8\n",
"2020-04-18 9\n",
"2020-04-25 9\n",
"2020-05-02 9\n",
"2020-05-09 10\n",
"2020-05-16 10\n",
"2020-05-23 10\n",
"2020-05-30 10\n",
"2020-06-06 10\n",
"2020-06-13 12\n",
"2020-06-20 12\n",
"2020-06-27 14\n",
"2020-07-04 16\n",
"2020-07-11 17\n",
"2020-07-18 18\n",
"2020-07-25 20\n",
"2020-08-01 24\n",
"2020-08-08 26\n",
"2020-08-15 28\n",
"2020-08-22 31\n",
"2020-08-29 37\n",
"2020-09-05 42\n",
"2020-09-12 44\n",
"2020-09-19 45\n",
"2020-09-26 52\n",
"2020-10-03 58\n",
"2020-10-10 60\n",
"2020-10-17 67\n",
"2020-10-24 68\n",
"2020-10-31 82\n",
"2020-11-07 84\n",
"2020-11-14 98\n",
"Name: Alaska: Cumulative deaths, dtype: int64"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
" getRS('D',Rstates[1])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"data= getFS('D', Fmodels[1], Fstates[1], FD.forecast_date[1])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 74., 67., 71., 78., 84.],\n",
" [ 81., 67., 75., 89., 105.],\n",
" [ 89., 67., 79., 101., 123.],\n",
" [ 99., 67., 81., 111., 141.]])"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.values"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2020-10-24 00:00:00\n",
"2020-10-31 00:00:00\n",
"2020-11-07 00:00:00\n",
"2020-11-14 00:00:00\n"
]
}
],
"source": [
"for i in data.index.tolist():\n",
" print(i)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"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>point</th>\n",
" <th>quantile_0.025</th>\n",
" <th>quantile_0.25</th>\n",
" <th>quantile_0.75</th>\n",
" <th>quantile_0.975</th>\n",
" </tr>\n",
" <tr>\n",
" <th>target_week_end_date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>2020-10-24</td>\n",
" <td>74.0</td>\n",
" <td>67.0</td>\n",
" <td>71.0</td>\n",
" <td>78.0</td>\n",
" <td>84.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-10-31</td>\n",
" <td>81.0</td>\n",
" <td>67.0</td>\n",
" <td>75.0</td>\n",
" <td>89.0</td>\n",
" <td>105.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-11-07</td>\n",
" <td>89.0</td>\n",
" <td>67.0</td>\n",
" <td>79.0</td>\n",
" <td>101.0</td>\n",
" <td>123.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-11-14</td>\n",
" <td>99.0</td>\n",
" <td>67.0</td>\n",
" <td>81.0</td>\n",
" <td>111.0</td>\n",
" <td>141.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" point quantile_0.025 quantile_0.25 quantile_0.75 \\\n",
"target_week_end_date \n",
"2020-10-24 74.0 67.0 71.0 78.0 \n",
"2020-10-31 81.0 67.0 75.0 89.0 \n",
"2020-11-07 89.0 67.0 79.0 101.0 \n",
"2020-11-14 99.0 67.0 81.0 111.0 \n",
"\n",
" quantile_0.975 \n",
"target_week_end_date \n",
"2020-10-24 84.0 \n",
"2020-10-31 105.0 \n",
"2020-11-07 123.0 \n",
"2020-11-14 141.0 "
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"pandas.core.frame.DataFrame"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(data)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"ename": "AttributeError",
"evalue": "'Timestamp' object has no attribute 'split'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-51-a8ece29f578b>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtolist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32m<ipython-input-51-a8ece29f578b>\u001b[0m in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtolist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m: 'Timestamp' object has no attribute 'split'"
]
}
],
"source": [
"[i.split() for i in data.index.tolist()]"
]
},
{
"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>point</th>\n",
" <th>quantile_0.025</th>\n",
" <th>quantile_0.25</th>\n",
" <th>quantile_0.75</th>\n",
" <th>quantile_0.975</th>\n",
" </tr>\n",
" <tr>\n",
" <th>target_week_end_date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>2020-10-24</td>\n",
" <td>74.0</td>\n",
" <td>67.0</td>\n",
" <td>71.0</td>\n",
" <td>78.0</td>\n",
" <td>84.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-10-31</td>\n",
" <td>81.0</td>\n",
" <td>67.0</td>\n",
" <td>75.0</td>\n",
" <td>89.0</td>\n",
" <td>105.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-11-07</td>\n",
" <td>89.0</td>\n",
" <td>67.0</td>\n",
" <td>79.0</td>\n",
" <td>101.0</td>\n",
" <td>123.0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2020-11-14</td>\n",
" <td>99.0</td>\n",
" <td>67.0</td>\n",
" <td>81.0</td>\n",
" <td>111.0</td>\n",
" <td>141.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" point quantile_0.025 quantile_0.25 quantile_0.75 \\\n",
"target_week_end_date \n",
"2020-10-24 74.0 67.0 71.0 78.0 \n",
"2020-10-31 81.0 67.0 75.0 89.0 \n",
"2020-11-07 89.0 67.0 79.0 101.0 \n",
"2020-11-14 99.0 67.0 81.0 111.0 \n",
"\n",
" quantile_0.975 \n",
"target_week_end_date \n",
"2020-10-24 84.0 \n",
"2020-10-31 105.0 \n",
"2020-11-07 123.0 \n",
"2020-11-14 141.0 "
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"DatetimeIndex(['2020-10-24', '2020-10-31', '2020-11-07', '2020-11-14'], dtype='datetime64[ns]', name='target_week_end_date', freq=None)"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.index"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'2020-10-31 00:00:00'"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"str(data.index[1])"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2020-10-24 00:00:00\n",
"2020-10-31 00:00:00\n",
"2020-11-07 00:00:00\n",
"2020-11-14 00:00:00\n"
]
}
],
"source": [
" for i in pd.Series(data.index.tolist()):\n",
" print(i)"
]
},
{
"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": "3.7.4"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue View Git Blame Copy Permalink