{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19", "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/kaggle/input/covid19-local-us-ca-forecasting-week-1/ca_train.csv\n", "/kaggle/input/covid19-local-us-ca-forecasting-week-1/ca_test.csv\n", "/kaggle/input/covid19-local-us-ca-forecasting-week-1/ca_submission.csv\n" ] } ], "source": [ "# This Python 3 environment comes with many helpful analytics libraries installed\n", "# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n", "# For example, here's several helpful packages to load in \n", "\n", "import numpy as np # linear algebra\n", "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n", "\n", "# Input data files are available in the \"../input/\" directory.\n", "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n", "\n", "import os\n", "for dirname, _, filenames in os.walk('/kaggle/input'):\n", " for filename in filenames:\n", " print(os.path.join(dirname, filename))\n", "\n", "train = pd.read_csv('../input/covid19-local-us-ca-forecasting-week-1/ca_train.csv')\n", "test = pd.read_csv('../input/covid19-local-us-ca-forecasting-week-1/ca_test.csv')\n", "sub = pd.read_csv('../input/covid19-local-us-ca-forecasting-week-1/ca_submission.csv')" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0", "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/opt/conda/lib/python3.6/site-packages/ipykernel_launcher.py:22: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "/opt/conda/lib/python3.6/site-packages/ipykernel_launcher.py:23: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ForecastIdProvince/StateCountry/RegionLatLongDateIdLogConfConfirmedCasesFatalities
01CaliforniaUS36.1162-119.68162020-03-12515.424030221.04.0
12CaliforniaUS36.1162-119.68162020-03-13525.627296282.04.0
23CaliforniaUS36.1162-119.68162020-03-14535.830561340.05.0
34CaliforniaUS36.1162-119.68162020-03-15546.033827426.06.0
45CaliforniaUS36.1162-119.68162020-03-16556.237093557.07.0
56CaliforniaUS36.1162-119.68162020-03-17566.440358698.012.0
67CaliforniaUS36.1162-119.68162020-03-18576.643624751.013.0
78CaliforniaUS36.1162-119.68162020-03-19586.846889952.018.0
89CaliforniaUS36.1162-119.68162020-03-20597.0501551177.023.0
910CaliforniaUS36.1162-119.68162020-03-21607.2534201364.024.0
1011CaliforniaUS36.1162-119.68162020-03-22617.4566861642.030.0
1112CaliforniaUS36.1162-119.68162020-03-23627.6599512108.039.0
1213CaliforniaUS36.1162-119.68162020-03-24637.8632172538.050.0
1314CaliforniaUS36.1162-119.68162020-03-25648.0664823185.061.0
1415CaliforniaUS36.1162-119.68162020-03-26658.2697483903.075.0
1516CaliforniaUS36.1162-119.68162020-03-27668.4730134783.092.0
1617CaliforniaUS36.1162-119.68162020-03-28678.6762795862.0113.0
1718CaliforniaUS36.1162-119.68162020-03-29688.8795447183.0139.0
1819CaliforniaUS36.1162-119.68162020-03-30699.0828108802.0171.0
1920CaliforniaUS36.1162-119.68162020-03-31709.28607510786.0210.0
2021CaliforniaUS36.1162-119.68162020-04-01719.48934113218.0258.0
2122CaliforniaUS36.1162-119.68162020-04-02729.69260616197.0317.0
2223CaliforniaUS36.1162-119.68162020-04-03739.89587219848.0389.0
2324CaliforniaUS36.1162-119.68162020-04-047410.09913724322.0477.0
2425CaliforniaUS36.1162-119.68162020-04-057510.30240329804.0584.0
2526CaliforniaUS36.1162-119.68162020-04-067610.50566836521.0717.0
2627CaliforniaUS36.1162-119.68162020-04-077710.70893444753.0879.0
2728CaliforniaUS36.1162-119.68162020-04-087810.91219954841.01077.0
2829CaliforniaUS36.1162-119.68162020-04-097911.11546567202.01320.0
2930CaliforniaUS36.1162-119.68162020-04-108011.31873082349.01619.0
3031CaliforniaUS36.1162-119.68162020-04-118111.521996100911.01984.0
3132CaliforniaUS36.1162-119.68162020-04-128211.725261123656.02431.0
3233CaliforniaUS36.1162-119.68162020-04-138311.928527151528.02980.0
3334CaliforniaUS36.1162-119.68162020-04-148412.131792185682.03652.0
3435CaliforniaUS36.1162-119.68162020-04-158512.335058227534.04476.0
3536CaliforniaUS36.1162-119.68162020-04-168612.538323278820.05485.0
3637CaliforniaUS36.1162-119.68162020-04-178712.741589341666.06722.0
3738CaliforniaUS36.1162-119.68162020-04-188812.944854418676.08237.0
3839CaliforniaUS36.1162-119.68162020-04-198913.148120513045.010095.0
3940CaliforniaUS36.1162-119.68162020-04-209013.351385628684.012370.0
4041CaliforniaUS36.1162-119.68162020-04-219113.554651770389.015159.0
4142CaliforniaUS36.1162-119.68162020-04-229213.757917944033.018576.0
4243CaliforniaUS36.1162-119.68162020-04-239313.9611821156816.022764.0
\n", "
" ], "text/plain": [ " ForecastId Province/State Country/Region Lat Long Date \\\n", "0 1 California US 36.1162 -119.6816 2020-03-12 \n", "1 2 California US 36.1162 -119.6816 2020-03-13 \n", "2 3 California US 36.1162 -119.6816 2020-03-14 \n", "3 4 California US 36.1162 -119.6816 2020-03-15 \n", "4 5 California US 36.1162 -119.6816 2020-03-16 \n", "5 6 California US 36.1162 -119.6816 2020-03-17 \n", "6 7 California US 36.1162 -119.6816 2020-03-18 \n", "7 8 California US 36.1162 -119.6816 2020-03-19 \n", "8 9 California US 36.1162 -119.6816 2020-03-20 \n", "9 10 California US 36.1162 -119.6816 2020-03-21 \n", "10 11 California US 36.1162 -119.6816 2020-03-22 \n", "11 12 California US 36.1162 -119.6816 2020-03-23 \n", "12 13 California US 36.1162 -119.6816 2020-03-24 \n", "13 14 California US 36.1162 -119.6816 2020-03-25 \n", "14 15 California US 36.1162 -119.6816 2020-03-26 \n", "15 16 California US 36.1162 -119.6816 2020-03-27 \n", "16 17 California US 36.1162 -119.6816 2020-03-28 \n", "17 18 California US 36.1162 -119.6816 2020-03-29 \n", "18 19 California US 36.1162 -119.6816 2020-03-30 \n", "19 20 California US 36.1162 -119.6816 2020-03-31 \n", "20 21 California US 36.1162 -119.6816 2020-04-01 \n", "21 22 California US 36.1162 -119.6816 2020-04-02 \n", "22 23 California US 36.1162 -119.6816 2020-04-03 \n", "23 24 California US 36.1162 -119.6816 2020-04-04 \n", "24 25 California US 36.1162 -119.6816 2020-04-05 \n", "25 26 California US 36.1162 -119.6816 2020-04-06 \n", "26 27 California US 36.1162 -119.6816 2020-04-07 \n", "27 28 California US 36.1162 -119.6816 2020-04-08 \n", "28 29 California US 36.1162 -119.6816 2020-04-09 \n", "29 30 California US 36.1162 -119.6816 2020-04-10 \n", "30 31 California US 36.1162 -119.6816 2020-04-11 \n", "31 32 California US 36.1162 -119.6816 2020-04-12 \n", "32 33 California US 36.1162 -119.6816 2020-04-13 \n", "33 34 California US 36.1162 -119.6816 2020-04-14 \n", "34 35 California US 36.1162 -119.6816 2020-04-15 \n", "35 36 California US 36.1162 -119.6816 2020-04-16 \n", "36 37 California US 36.1162 -119.6816 2020-04-17 \n", "37 38 California US 36.1162 -119.6816 2020-04-18 \n", "38 39 California US 36.1162 -119.6816 2020-04-19 \n", "39 40 California US 36.1162 -119.6816 2020-04-20 \n", "40 41 California US 36.1162 -119.6816 2020-04-21 \n", "41 42 California US 36.1162 -119.6816 2020-04-22 \n", "42 43 California US 36.1162 -119.6816 2020-04-23 \n", "\n", " Id LogConf ConfirmedCases Fatalities \n", "0 51 5.424030 221.0 4.0 \n", "1 52 5.627296 282.0 4.0 \n", "2 53 5.830561 340.0 5.0 \n", "3 54 6.033827 426.0 6.0 \n", "4 55 6.237093 557.0 7.0 \n", "5 56 6.440358 698.0 12.0 \n", "6 57 6.643624 751.0 13.0 \n", "7 58 6.846889 952.0 18.0 \n", "8 59 7.050155 1177.0 23.0 \n", "9 60 7.253420 1364.0 24.0 \n", "10 61 7.456686 1642.0 30.0 \n", "11 62 7.659951 2108.0 39.0 \n", "12 63 7.863217 2538.0 50.0 \n", "13 64 8.066482 3185.0 61.0 \n", "14 65 8.269748 3903.0 75.0 \n", "15 66 8.473013 4783.0 92.0 \n", "16 67 8.676279 5862.0 113.0 \n", "17 68 8.879544 7183.0 139.0 \n", "18 69 9.082810 8802.0 171.0 \n", "19 70 9.286075 10786.0 210.0 \n", "20 71 9.489341 13218.0 258.0 \n", "21 72 9.692606 16197.0 317.0 \n", "22 73 9.895872 19848.0 389.0 \n", "23 74 10.099137 24322.0 477.0 \n", "24 75 10.302403 29804.0 584.0 \n", "25 76 10.505668 36521.0 717.0 \n", "26 77 10.708934 44753.0 879.0 \n", "27 78 10.912199 54841.0 1077.0 \n", "28 79 11.115465 67202.0 1320.0 \n", "29 80 11.318730 82349.0 1619.0 \n", "30 81 11.521996 100911.0 1984.0 \n", "31 82 11.725261 123656.0 2431.0 \n", "32 83 11.928527 151528.0 2980.0 \n", "33 84 12.131792 185682.0 3652.0 \n", "34 85 12.335058 227534.0 4476.0 \n", "35 86 12.538323 278820.0 5485.0 \n", "36 87 12.741589 341666.0 6722.0 \n", "37 88 12.944854 418676.0 8237.0 \n", "38 89 13.148120 513045.0 10095.0 \n", "39 90 13.351385 628684.0 12370.0 \n", "40 91 13.554651 770389.0 15159.0 \n", "41 92 13.757917 944033.0 18576.0 \n", "42 93 13.961182 1156816.0 22764.0 " ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.linear_model import LinearRegression\n", "train=train[train.ConfirmedCases>0]\n", "\n", "model_cc= LinearRegression()\n", "x1=np.array(train.Id).reshape(-1,1)\n", "y1=np.log(train.ConfirmedCases)\n", "model_cc.fit(x1,y1)\n", "\n", "model_fc= LinearRegression()\n", "x2=np.array(train.ConfirmedCases).reshape(-1,1)\n", "y2=train.Fatalities\n", "model_fc.fit(x2,y2)\n", "\n", "test[\"Id\"]=50+test.ForecastId\n", "test.head()\n", "\n", "test[\"LogConf\"]=model_cc.predict(np.array(test.Id).reshape(-1,1))\n", "test[\"ConfirmedCases\"]=np.exp(test.LogConf)//1\n", "test[\"Fatalities\"]=model_fc.predict(np.array(test.ConfirmedCases).reshape(-1,1))//1\n", "\n", "for id in train.Id:\n", " test.ConfirmedCases[test.Id==id]=train.ConfirmedCases[train.Id==id].sum()\n", " test.Fatalities[test.Id==id]=train.Fatalities[train.Id==id].sum()\n", "test" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "sub.ConfirmedCases=test.ConfirmedCases\n", "sub.Fatalities=test.Fatalities\n", "sub.to_csv(\"submission.csv\", index=False)" ] }, { "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": "3.6.6" } }, "nbformat": 4, "nbformat_minor": 4 }