diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 68b3762..479d77d 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -12,11 +12,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, "outputs": [], "source": [ - "#Import your libraries\n" + "# Libraries\n", + "import math\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import scipy.stats as st\n", + "import statsmodels.api as sm\n", + "import statsmodels.formula.api as smf\n", + "pd.set_option('display.max_columns', None)\n", + "# pd.reset_option('display.max_columns')" ] }, { @@ -38,11 +47,240 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercentSeaLevelPressureHighInchesSeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEvents
02013-12-2174604567494393755729.8629.6829.591072204310.46Rain , Thunderstorm
12013-12-2256483943362893684330.4130.1329.8710105166250
22013-12-2358453231272376522730.5630.4930.4110101083120
32013-12-2461463136282189562230.5630.4530.310107124200
42013-12-2558504144403686715630.4130.3330.271010710216T
\n", + "
" + ], + "text/plain": [ + " Date TempHighF TempAvgF TempLowF DewPointHighF DewPointAvgF \\\n", + "0 2013-12-21 74 60 45 67 49 \n", + "1 2013-12-22 56 48 39 43 36 \n", + "2 2013-12-23 58 45 32 31 27 \n", + "3 2013-12-24 61 46 31 36 28 \n", + "4 2013-12-25 58 50 41 44 40 \n", + "\n", + " DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent \\\n", + "0 43 93 75 57 \n", + "1 28 93 68 43 \n", + "2 23 76 52 27 \n", + "3 21 89 56 22 \n", + "4 36 86 71 56 \n", + "\n", + " SeaLevelPressureHighInches SeaLevelPressureAvgInches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " SeaLevelPressureLowInches VisibilityHighMiles VisibilityAvgMiles \\\n", + "0 29.59 10 7 \n", + "1 29.87 10 10 \n", + "2 30.41 10 10 \n", + "3 30.3 10 10 \n", + "4 30.27 10 10 \n", + "\n", + " VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH \\\n", + "0 2 20 4 31 \n", + "1 5 16 6 25 \n", + "2 10 8 3 12 \n", + "3 7 12 4 20 \n", + "4 7 10 2 16 \n", + "\n", + " PrecipitationSumInches Events \n", + "0 0.46 Rain , Thunderstorm \n", + "1 0 \n", + "2 0 \n", + "3 0 \n", + "4 T " + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Your code here\n", + "austin=pd.read_csv(\"austin_weather.csv\")\n", + "austin.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 58, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "df=austin.copy()" ] }, { @@ -57,29 +295,195 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 59, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 1319 entries, 0 to 1318\n", + "Data columns (total 21 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 Date 1319 non-null object\n", + " 1 TempHighF 1319 non-null int64 \n", + " 2 TempAvgF 1319 non-null int64 \n", + " 3 TempLowF 1319 non-null int64 \n", + " 4 DewPointHighF 1319 non-null object\n", + " 5 DewPointAvgF 1319 non-null object\n", + " 6 DewPointLowF 1319 non-null object\n", + " 7 HumidityHighPercent 1319 non-null object\n", + " 8 HumidityAvgPercent 1319 non-null object\n", + " 9 HumidityLowPercent 1319 non-null object\n", + " 10 SeaLevelPressureHighInches 1319 non-null object\n", + " 11 SeaLevelPressureAvgInches 1319 non-null object\n", + " 12 SeaLevelPressureLowInches 1319 non-null object\n", + " 13 VisibilityHighMiles 1319 non-null object\n", + " 14 VisibilityAvgMiles 1319 non-null object\n", + " 15 VisibilityLowMiles 1319 non-null object\n", + " 16 WindHighMPH 1319 non-null object\n", + " 17 WindAvgMPH 1319 non-null object\n", + " 18 WindGustMPH 1319 non-null object\n", + " 19 PrecipitationSumInches 1319 non-null object\n", + " 20 Events 1319 non-null object\n", + "dtypes: int64(3), object(18)\n", + "memory usage: 216.5+ KB\n" + ] + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df.info()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 60, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Date 1319\n", + "TempHighF 74\n", + "TempAvgF 64\n", + "TempLowF 61\n", + "DewPointHighF 64\n", + "DewPointAvgF 66\n", + "DewPointLowF 73\n", + "HumidityHighPercent 58\n", + "HumidityAvgPercent 69\n", + "HumidityLowPercent 82\n", + "SeaLevelPressureHighInches 105\n", + "SeaLevelPressureAvgInches 101\n", + "SeaLevelPressureLowInches 105\n", + "VisibilityHighMiles 5\n", + "VisibilityAvgMiles 10\n", + "VisibilityLowMiles 12\n", + "WindHighMPH 22\n", + "WindAvgMPH 13\n", + "WindGustMPH 37\n", + "PrecipitationSumInches 114\n", + "Events 9\n", + "dtype: int64" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df.nunique()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 61, "metadata": {}, - "outputs": [], + "outputs": [ + { + "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", + "
TempHighFTempAvgFTempLowF
count1319.0000001319.0000001319.000000
mean80.86277570.64291159.902957
std14.76652314.04590414.190648
min32.00000029.00000019.000000
25%72.00000062.00000049.000000
50%83.00000073.00000063.000000
75%92.00000083.00000073.000000
max107.00000093.00000081.000000
\n", + "
" + ], + "text/plain": [ + " TempHighF TempAvgF TempLowF\n", + "count 1319.000000 1319.000000 1319.000000\n", + "mean 80.862775 70.642911 59.902957\n", + "std 14.766523 14.045904 14.190648\n", + "min 32.000000 29.000000 19.000000\n", + "25% 72.000000 62.000000 49.000000\n", + "50% 83.000000 73.000000 63.000000\n", + "75% 92.000000 83.000000 73.000000\n", + "max 107.000000 93.000000 81.000000" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df.describe()" ] }, { @@ -113,20 +517,40 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 62, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array(['49', '36', '27', '28', '40', '39', '41', '26', '42', '22', '48',\n", + " '32', '8', '11', '45', '55', '61', '37', '47', '25', '23', '20',\n", + " '33', '30', '29', '17', '14', '13', '54', '59', '15', '24', '34',\n", + " '35', '57', '50', '53', '60', '46', '56', '51', '31', '38', '62',\n", + " '43', '63', '64', '67', '66', '58', '70', '68', '65', '69', '71',\n", + " '72', '-', '73', '74', '21', '44', '52', '12', '75', '76', '18'],\n", + " dtype=object)" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df.DewPointAvgF.unique()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 63, "metadata": {}, "outputs": [], "source": [ - "# Your observation here\n" + "# Your observation here \n", + "# There is a hyphen that is preventing pandas\n", + "# to convert the column to numeric type" ] }, { @@ -140,7 +564,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 64, "metadata": {}, "outputs": [], "source": [ @@ -153,11 +577,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 65, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "# Your code here\n", + "df1=df.copy()\n" ] }, { @@ -169,11 +594,56 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 66, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "# Your code here\n", + "df1[wrong_type_columns]=df1[wrong_type_columns].apply(pd.to_numeric, errors=\"coerce\")" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 1319 entries, 0 to 1318\n", + "Data columns (total 21 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 Date 1319 non-null object \n", + " 1 TempHighF 1319 non-null int64 \n", + " 2 TempAvgF 1319 non-null int64 \n", + " 3 TempLowF 1319 non-null int64 \n", + " 4 DewPointHighF 1312 non-null float64\n", + " 5 DewPointAvgF 1312 non-null float64\n", + " 6 DewPointLowF 1312 non-null float64\n", + " 7 HumidityHighPercent 1317 non-null float64\n", + " 8 HumidityAvgPercent 1317 non-null float64\n", + " 9 HumidityLowPercent 1317 non-null float64\n", + " 10 SeaLevelPressureHighInches 1316 non-null float64\n", + " 11 SeaLevelPressureAvgInches 1316 non-null float64\n", + " 12 SeaLevelPressureLowInches 1316 non-null float64\n", + " 13 VisibilityHighMiles 1307 non-null float64\n", + " 14 VisibilityAvgMiles 1307 non-null float64\n", + " 15 VisibilityLowMiles 1307 non-null float64\n", + " 16 WindHighMPH 1317 non-null float64\n", + " 17 WindAvgMPH 1317 non-null float64\n", + " 18 WindGustMPH 1315 non-null float64\n", + " 19 PrecipitationSumInches 1195 non-null float64\n", + " 20 Events 1319 non-null object \n", + "dtypes: float64(16), int64(3), object(2)\n", + "memory usage: 216.5+ KB\n" + ] + } + ], + "source": [ + "df1.info()" ] }, { @@ -200,11 +670,488 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 68, + "metadata": {}, + "outputs": [], + "source": [ + "df2=df1.copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 69, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "# Your code here\n", + "df2[\"null\"]=df2.isnull().any(axis=1)" + ] + }, + { + "cell_type": "code", + "execution_count": 80, + "metadata": {}, + "outputs": [ + { + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercentSeaLevelPressureHighInchesSeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEventsnull
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.00.46Rain , ThunderstormFalse
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.00.00False
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.00.00False
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.00.00False
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0NaNTrue
\n", + "
" + ], + "text/plain": [ + " Date TempHighF TempAvgF TempLowF DewPointHighF DewPointAvgF \\\n", + "0 2013-12-21 74 60 45 67.0 49.0 \n", + "1 2013-12-22 56 48 39 43.0 36.0 \n", + "2 2013-12-23 58 45 32 31.0 27.0 \n", + "3 2013-12-24 61 46 31 36.0 28.0 \n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "\n", + " DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent \\\n", + "0 43.0 93.0 75.0 57.0 \n", + "1 28.0 93.0 68.0 43.0 \n", + "2 23.0 76.0 52.0 27.0 \n", + "3 21.0 89.0 56.0 22.0 \n", + "4 36.0 86.0 71.0 56.0 \n", + "\n", + " SeaLevelPressureHighInches SeaLevelPressureAvgInches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " SeaLevelPressureLowInches VisibilityHighMiles VisibilityAvgMiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "\n", + " VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH \\\n", + "0 2.0 20.0 4.0 31.0 \n", + "1 5.0 16.0 6.0 25.0 \n", + "2 10.0 8.0 3.0 12.0 \n", + "3 7.0 12.0 4.0 20.0 \n", + "4 7.0 10.0 2.0 16.0 \n", + "\n", + " PrecipitationSumInches Events null \n", + "0 0.46 Rain , Thunderstorm False \n", + "1 0.00 False \n", + "2 0.00 False \n", + "3 0.00 False \n", + "4 NaN True " + ] + }, + "execution_count": 80, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": {}, + "outputs": [ + { + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercentSeaLevelPressureHighInchesSeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEventsnull
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0NaNTrue
62013-12-2760534541.039.037.083.065.047.030.4630.3930.3410.09.07.07.01.011.0NaNTrue
72013-12-2862514043.039.033.092.064.036.030.3330.1730.0410.010.07.010.02.014.0NaNTrue
422014-02-0176665562.059.041.081.071.060.029.9129.8129.7510.010.09.014.06.026.0NaNRainTrue
512014-02-1060483549.036.030.082.074.066.030.2330.1530.0210.08.04.015.09.023.0NaNRainTrue
\n", + "
" + ], + "text/plain": [ + " Date TempHighF TempAvgF TempLowF DewPointHighF DewPointAvgF \\\n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "6 2013-12-27 60 53 45 41.0 39.0 \n", + "7 2013-12-28 62 51 40 43.0 39.0 \n", + "42 2014-02-01 76 66 55 62.0 59.0 \n", + "51 2014-02-10 60 48 35 49.0 36.0 \n", + "\n", + " DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent \\\n", + "4 36.0 86.0 71.0 56.0 \n", + "6 37.0 83.0 65.0 47.0 \n", + "7 33.0 92.0 64.0 36.0 \n", + "42 41.0 81.0 71.0 60.0 \n", + "51 30.0 82.0 74.0 66.0 \n", + "\n", + " SeaLevelPressureHighInches SeaLevelPressureAvgInches \\\n", + "4 30.41 30.33 \n", + "6 30.46 30.39 \n", + "7 30.33 30.17 \n", + "42 29.91 29.81 \n", + "51 30.23 30.15 \n", + "\n", + " SeaLevelPressureLowInches VisibilityHighMiles VisibilityAvgMiles \\\n", + "4 30.27 10.0 10.0 \n", + "6 30.34 10.0 9.0 \n", + "7 30.04 10.0 10.0 \n", + "42 29.75 10.0 10.0 \n", + "51 30.02 10.0 8.0 \n", + "\n", + " VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH \\\n", + "4 7.0 10.0 2.0 16.0 \n", + "6 7.0 7.0 1.0 11.0 \n", + "7 7.0 10.0 2.0 14.0 \n", + "42 9.0 14.0 6.0 26.0 \n", + "51 4.0 15.0 9.0 23.0 \n", + "\n", + " PrecipitationSumInches Events null \n", + "4 NaN True \n", + "6 NaN True \n", + "7 NaN True \n", + "42 NaN Rain True \n", + "51 NaN Rain True " + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2_null=df2[df2[\"null\"]==True]\n", + "df2_null.head()" ] }, { @@ -233,11 +1180,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 84, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "136" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "len(df2_null)" ] }, { @@ -249,11 +1208,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 85, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.10310841546626232" + ] + }, + "execution_count": 85, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "len(df2_null)/len(df2)" ] }, { @@ -267,11 +1238,95 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 92, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "# Your code here\n", + "df2.columns=df2.columns.str.lower().str.replace(\" \",\"_\")" + ] + }, + { + "cell_type": "code", + "execution_count": 93, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['date',\n", + " 'temphighf',\n", + " 'tempavgf',\n", + " 'templowf',\n", + " 'dewpointhighf',\n", + " 'dewpointavgf',\n", + " 'dewpointlowf',\n", + " 'humidityhighpercent',\n", + " 'humidityavgpercent',\n", + " 'humiditylowpercent',\n", + " 'sealevelpressurehighinches',\n", + " 'sealevelpressureavginches',\n", + " 'sealevelpressurelowinches',\n", + " 'visibilityhighmiles',\n", + " 'visibilityavgmiles',\n", + " 'visibilitylowmiles',\n", + " 'windhighmph',\n", + " 'windavgmph',\n", + " 'windgustmph',\n", + " 'precipitationsuminches',\n", + " 'events',\n", + " 'null']" + ] + }, + "execution_count": 93, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.columns.to_list()" + ] + }, + { + "cell_type": "code", + "execution_count": 170, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "date 0\n", + "temphighf 0\n", + "tempavgf 0\n", + "templowf 0\n", + "dewpointhighf 7\n", + "dewpointavgf 7\n", + "dewpointlowf 7\n", + "humidityhighpercent 2\n", + "humidityavgpercent 2\n", + "humiditylowpercent 2\n", + "sealevelpressurehighinches 3\n", + "sealevelpressureavginches 3\n", + "sealevelpressurelowinches 3\n", + "visibilityhighmiles 12\n", + "visibilityavgmiles 12\n", + "visibilitylowmiles 12\n", + "windhighmph 2\n", + "windavgmph 2\n", + "windgustmph 4\n", + "precipitationsuminches 124\n", + "events 0\n", + "null 0\n", + "dtype: int64" + ] + }, + "execution_count": 170, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.isna().sum()" ] }, { @@ -283,11 +1338,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 120, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.09401061410159212" + ] + }, + "execution_count": 120, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df2.precipitationsuminches.isna().sum()/len(df2.precipitationsuminches)" ] }, { @@ -309,16 +1376,439 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 125, "metadata": {}, - "outputs": [], + "outputs": [ + { + "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", + "
datetemphighftempavgftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmpheventsnull
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0Rain , ThunderstormFalse
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True
..................................................................
13142017-07-27103897571.067.061.082.054.025.030.0429.9729.8810.010.010.012.05.021.0False
13152017-07-28105917671.064.055.087.054.020.029.9729.9029.8110.010.010.014.05.020.0False
13162017-07-29107927772.064.055.082.051.019.029.9129.8629.7910.010.010.012.04.017.0False
13172017-07-30106937970.068.063.069.048.027.029.9629.9129.8710.010.010.013.04.020.0False
13182017-07-3199887766.061.054.064.043.022.030.0429.9729.9110.010.010.012.04.020.0False
\n", + "

1319 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " date temphighf tempavgf templowf dewpointhighf dewpointavgf \\\n", + "0 2013-12-21 74 60 45 67.0 49.0 \n", + "1 2013-12-22 56 48 39 43.0 36.0 \n", + "2 2013-12-23 58 45 32 31.0 27.0 \n", + "3 2013-12-24 61 46 31 36.0 28.0 \n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "... ... ... ... ... ... ... \n", + "1314 2017-07-27 103 89 75 71.0 67.0 \n", + "1315 2017-07-28 105 91 76 71.0 64.0 \n", + "1316 2017-07-29 107 92 77 72.0 64.0 \n", + "1317 2017-07-30 106 93 79 70.0 68.0 \n", + "1318 2017-07-31 99 88 77 66.0 61.0 \n", + "\n", + " dewpointlowf humidityhighpercent humidityavgpercent \\\n", + "0 43.0 93.0 75.0 \n", + "1 28.0 93.0 68.0 \n", + "2 23.0 76.0 52.0 \n", + "3 21.0 89.0 56.0 \n", + "4 36.0 86.0 71.0 \n", + "... ... ... ... \n", + "1314 61.0 82.0 54.0 \n", + "1315 55.0 87.0 54.0 \n", + "1316 55.0 82.0 51.0 \n", + "1317 63.0 69.0 48.0 \n", + "1318 54.0 64.0 43.0 \n", + "\n", + " humiditylowpercent sealevelpressurehighinches \\\n", + "0 57.0 29.86 \n", + "1 43.0 30.41 \n", + "2 27.0 30.56 \n", + "3 22.0 30.56 \n", + "4 56.0 30.41 \n", + "... ... ... \n", + "1314 25.0 30.04 \n", + "1315 20.0 29.97 \n", + "1316 19.0 29.91 \n", + "1317 27.0 29.96 \n", + "1318 22.0 30.04 \n", + "\n", + " sealevelpressureavginches sealevelpressurelowinches \\\n", + "0 29.68 29.59 \n", + "1 30.13 29.87 \n", + "2 30.49 30.41 \n", + "3 30.45 30.30 \n", + "4 30.33 30.27 \n", + "... ... ... \n", + "1314 29.97 29.88 \n", + "1315 29.90 29.81 \n", + "1316 29.86 29.79 \n", + "1317 29.91 29.87 \n", + "1318 29.97 29.91 \n", + "\n", + " visibilityhighmiles visibilityavgmiles visibilitylowmiles \\\n", + "0 10.0 7.0 2.0 \n", + "1 10.0 10.0 5.0 \n", + "2 10.0 10.0 10.0 \n", + "3 10.0 10.0 7.0 \n", + "4 10.0 10.0 7.0 \n", + "... ... ... ... \n", + "1314 10.0 10.0 10.0 \n", + "1315 10.0 10.0 10.0 \n", + "1316 10.0 10.0 10.0 \n", + "1317 10.0 10.0 10.0 \n", + "1318 10.0 10.0 10.0 \n", + "\n", + " windhighmph windavgmph windgustmph events null \n", + "0 20.0 4.0 31.0 Rain , Thunderstorm False \n", + "1 16.0 6.0 25.0 False \n", + "2 8.0 3.0 12.0 False \n", + "3 12.0 4.0 20.0 False \n", + "4 10.0 2.0 16.0 True \n", + "... ... ... ... ... ... \n", + "1314 12.0 5.0 21.0 False \n", + "1315 14.0 5.0 20.0 False \n", + "1316 12.0 4.0 17.0 False \n", + "1317 13.0 4.0 20.0 False \n", + "1318 12.0 4.0 20.0 False \n", + "\n", + "[1319 rows x 21 columns]" + ] + }, + "execution_count": 125, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Your code here \n", - "\n", - "\n", + "df3=df2.copy()\n", + "df3=df3.drop(columns=\"precipitationsuminches\")\n", "# Print `austin` to confirm the column is indeed removed\n", "\n", - "austin" + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 133, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "903" + ] + }, + "execution_count": 133, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3.events.eq(\" \").sum() ## OJO CUIDAO, \n", + " ## Tendremos que limpiar\n", + " ## cuando lo mande el lab" ] }, { @@ -336,11 +1826,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 135, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_32932/4278860520.py:3: FutureWarning: DataFrame.interpolate with object dtype is deprecated and will raise in a future version. Call obj.infer_objects(copy=False) before interpolating instead.\n", + " df4_fixed=df4.interpolate()\n" + ] + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df4=df3.copy()\n", + "df4_fixed=df4.interpolate()" ] }, { @@ -352,11 +1853,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 139, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 139, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "df4_fixed.isnull().any(axis=1).sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 140, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "14" + ] + }, + "execution_count": 140, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df4.isnull().any(axis=1).sum()" ] }, { @@ -377,11 +1910,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 230, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "# Your code here:\n", + "df5=df4_fixed.copy()" ] }, { @@ -395,11 +1929,33 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 231, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "events\n", + " 903\n", + "Rain 192\n", + "Rain , Thunderstorm 137\n", + "Fog , Rain , Thunderstorm 33\n", + "Fog 21\n", + "Thunderstorm 17\n", + "Fog , Rain 14\n", + "Rain , Snow 1\n", + "Fog , Thunderstorm 1\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 231, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your answer:\n" + "# Your answer:\n", + "df5.events.value_counts()" ] }, { @@ -415,18 +1971,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 232, + "metadata": {}, + "outputs": [], + "source": [ + "# df5[\"events\"]=df5[\"events\"].replace(\" \",0)\n", + "# df5[\"events\"] = df5[\"events\"].str.split(\", \")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 233, + "metadata": {}, + "outputs": [], + "source": [ + "df6=df5.copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 234, "metadata": {}, "outputs": [], "source": [ - "event_list = ['Snow', 'Fog', 'Rain', 'Thunderstorm']\n", + "event_list = ['snow', 'fog', 'rain', 'thunderstorm']\n", "\n", "# Your code here\n", - "\n", - "\n", - "# Print your new dataframe to check whether new columns have been created:\n", - "\n", - "austin_fixed" + "for event in event_list:\n", + " df6[event]=0" ] }, { @@ -444,29 +2016,292 @@ "* What if the values you populated are booleans instead of numbers? You can cast the boolean values to numbers by using `.astype(int)`. For instance, `pd.Series([True, True, False]).astype(int)` will return a new series with values of `[1, 1, 0]`." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Print out `austin_fixed` to check if the event columns are populated with the intended values" + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 247, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "df6[\"rain\"] = df6[\"events\"].str.contains(\"Rain\", na=False).astype(int)\n", + "df6[\"snow\"] = df6[\"events\"].str.contains(\"Snow\", na=False).astype(int)\n", + "df6[\"fog\"] = df6[\"events\"].str.contains(\"Fog\", na=False).astype(int)\n", + "df6[\"thunderstorm\"] = df6[\"events\"].str.contains(\"Thunderstorm\", na=False).astype(int)\n", + "df6.rain=df6.rain.fillna(0)\n", + "df6.snow=df6.snow.fillna(0)\n", + "df6.fog=df6.fog.fillna(0)\n", + "df6.thunderstorm=df6.thunderstorm.fillna(0)" ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 248, "metadata": {}, + "outputs": [ + { + "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", + "
datetemphighftempavgftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmpheventsnullsnowfograinthunderstorm
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0Rain , ThunderstormFalse0011
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False0000
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False0000
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False0000
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True0000
\n", + "
" + ], + "text/plain": [ + " date temphighf tempavgf templowf dewpointhighf dewpointavgf \\\n", + "0 2013-12-21 74 60 45 67.0 49.0 \n", + "1 2013-12-22 56 48 39 43.0 36.0 \n", + "2 2013-12-23 58 45 32 31.0 27.0 \n", + "3 2013-12-24 61 46 31 36.0 28.0 \n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "\n", + " dewpointlowf humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 43.0 93.0 75.0 57.0 \n", + "1 28.0 93.0 68.0 43.0 \n", + "2 23.0 76.0 52.0 27.0 \n", + "3 21.0 89.0 56.0 22.0 \n", + "4 36.0 86.0 71.0 56.0 \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph \\\n", + "0 2.0 20.0 4.0 31.0 \n", + "1 5.0 16.0 6.0 25.0 \n", + "2 10.0 8.0 3.0 12.0 \n", + "3 7.0 12.0 4.0 20.0 \n", + "4 7.0 10.0 2.0 16.0 \n", + "\n", + " events null snow fog rain thunderstorm \n", + "0 Rain , Thunderstorm False 0 0 1 1 \n", + "1 False 0 0 0 0 \n", + "2 False 0 0 0 0 \n", + "3 False 0 0 0 0 \n", + "4 True 0 0 0 0 " + ] + }, + "execution_count": 248, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "#### Print out `austin_fixed` to check if the event columns are populated with the intended values" + "df6.head()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 249, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "## Solución de Fer. No me va \n", + "# a funcionar porque estandaricé columnas y los eventos\n", + "# (valores) están capitalizados pero el nombre de \n", + "# columna, no. \n", + "# for event in event_list:\n", + "# df6[event] = df6[\"events\"].str.contains(event,na=False).astype(int)" ] }, { @@ -476,13 +2311,527 @@ "#### If your code worked correctly, now we can drop the `Events` column as we don't need it any more." ] }, + { + "cell_type": "code", + "execution_count": 250, + "metadata": {}, + "outputs": [ + { + "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", + "
datetemphighftempavgftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmpheventsnullsnowfograinthunderstorm
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0Rain , ThunderstormFalse0011
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False0000
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False0000
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False0000
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True0000
\n", + "
" + ], + "text/plain": [ + " date temphighf tempavgf templowf dewpointhighf dewpointavgf \\\n", + "0 2013-12-21 74 60 45 67.0 49.0 \n", + "1 2013-12-22 56 48 39 43.0 36.0 \n", + "2 2013-12-23 58 45 32 31.0 27.0 \n", + "3 2013-12-24 61 46 31 36.0 28.0 \n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "\n", + " dewpointlowf humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 43.0 93.0 75.0 57.0 \n", + "1 28.0 93.0 68.0 43.0 \n", + "2 23.0 76.0 52.0 27.0 \n", + "3 21.0 89.0 56.0 22.0 \n", + "4 36.0 86.0 71.0 56.0 \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph \\\n", + "0 2.0 20.0 4.0 31.0 \n", + "1 5.0 16.0 6.0 25.0 \n", + "2 10.0 8.0 3.0 12.0 \n", + "3 7.0 12.0 4.0 20.0 \n", + "4 7.0 10.0 2.0 16.0 \n", + "\n", + " events null snow fog rain thunderstorm \n", + "0 Rain , Thunderstorm False 0 0 1 1 \n", + "1 False 0 0 0 0 \n", + "2 False 0 0 0 0 \n", + "3 False 0 0 0 0 \n", + "4 True 0 0 0 0 " + ] + }, + "execution_count": 250, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df6.head()" + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "KeyError", + "evalue": "\"['events'] not found in axis\"", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[252], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Your code here\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df6\u001b[38;5;241m=\u001b[39mdf6\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevents\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 3\u001b[0m df6\u001b[38;5;241m.\u001b[39mhead()\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/frame.py:5581\u001b[0m, in \u001b[0;36mDataFrame.drop\u001b[0;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[1;32m 5433\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdrop\u001b[39m(\n\u001b[1;32m 5434\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 5435\u001b[0m labels: IndexLabel \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 5442\u001b[0m errors: IgnoreRaise \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 5443\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 5444\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 5445\u001b[0m \u001b[38;5;124;03m Drop specified labels from rows or columns.\u001b[39;00m\n\u001b[1;32m 5446\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 5579\u001b[0m \u001b[38;5;124;03m weight 1.0 0.8\u001b[39;00m\n\u001b[1;32m 5580\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 5581\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mdrop(\n\u001b[1;32m 5582\u001b[0m labels\u001b[38;5;241m=\u001b[39mlabels,\n\u001b[1;32m 5583\u001b[0m axis\u001b[38;5;241m=\u001b[39maxis,\n\u001b[1;32m 5584\u001b[0m index\u001b[38;5;241m=\u001b[39mindex,\n\u001b[1;32m 5585\u001b[0m columns\u001b[38;5;241m=\u001b[39mcolumns,\n\u001b[1;32m 5586\u001b[0m level\u001b[38;5;241m=\u001b[39mlevel,\n\u001b[1;32m 5587\u001b[0m inplace\u001b[38;5;241m=\u001b[39minplace,\n\u001b[1;32m 5588\u001b[0m errors\u001b[38;5;241m=\u001b[39merrors,\n\u001b[1;32m 5589\u001b[0m )\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/generic.py:4788\u001b[0m, in \u001b[0;36mNDFrame.drop\u001b[0;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[1;32m 4786\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m axis, labels \u001b[38;5;129;01min\u001b[39;00m axes\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 4787\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m labels \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 4788\u001b[0m obj \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39m_drop_axis(labels, axis, level\u001b[38;5;241m=\u001b[39mlevel, errors\u001b[38;5;241m=\u001b[39merrors)\n\u001b[1;32m 4790\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inplace:\n\u001b[1;32m 4791\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_update_inplace(obj)\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/generic.py:4830\u001b[0m, in \u001b[0;36mNDFrame._drop_axis\u001b[0;34m(self, labels, axis, level, errors, only_slice)\u001b[0m\n\u001b[1;32m 4828\u001b[0m new_axis \u001b[38;5;241m=\u001b[39m axis\u001b[38;5;241m.\u001b[39mdrop(labels, level\u001b[38;5;241m=\u001b[39mlevel, errors\u001b[38;5;241m=\u001b[39merrors)\n\u001b[1;32m 4829\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 4830\u001b[0m new_axis \u001b[38;5;241m=\u001b[39m axis\u001b[38;5;241m.\u001b[39mdrop(labels, errors\u001b[38;5;241m=\u001b[39merrors)\n\u001b[1;32m 4831\u001b[0m indexer \u001b[38;5;241m=\u001b[39m axis\u001b[38;5;241m.\u001b[39mget_indexer(new_axis)\n\u001b[1;32m 4833\u001b[0m \u001b[38;5;66;03m# Case for non-unique axis\u001b[39;00m\n\u001b[1;32m 4834\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/indexes/base.py:7070\u001b[0m, in \u001b[0;36mIndex.drop\u001b[0;34m(self, labels, errors)\u001b[0m\n\u001b[1;32m 7068\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mask\u001b[38;5;241m.\u001b[39many():\n\u001b[1;32m 7069\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m-> 7070\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlabels[mask]\u001b[38;5;241m.\u001b[39mtolist()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m not found in axis\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 7071\u001b[0m indexer \u001b[38;5;241m=\u001b[39m indexer[\u001b[38;5;241m~\u001b[39mmask]\n\u001b[1;32m 7072\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdelete(indexer)\n", + "\u001b[0;31mKeyError\u001b[0m: \"['events'] not found in axis\"" + ] + } + ], + "source": [ + "# Your code here\n", + "df6=df6.drop(columns=\"events\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 253, + "metadata": {}, + "outputs": [ + { + "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", + "
datetemphighftempavgftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmphnullsnowfograinthunderstorm
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0False0011
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False0000
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False0000
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False0000
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True0000
\n", + "
" + ], + "text/plain": [ + " date temphighf tempavgf templowf dewpointhighf dewpointavgf \\\n", + "0 2013-12-21 74 60 45 67.0 49.0 \n", + "1 2013-12-22 56 48 39 43.0 36.0 \n", + "2 2013-12-23 58 45 32 31.0 27.0 \n", + "3 2013-12-24 61 46 31 36.0 28.0 \n", + "4 2013-12-25 58 50 41 44.0 40.0 \n", + "\n", + " dewpointlowf humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 43.0 93.0 75.0 57.0 \n", + "1 28.0 93.0 68.0 43.0 \n", + "2 23.0 76.0 52.0 27.0 \n", + "3 21.0 89.0 56.0 22.0 \n", + "4 36.0 86.0 71.0 56.0 \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph null snow fog \\\n", + "0 2.0 20.0 4.0 31.0 False 0 0 \n", + "1 5.0 16.0 6.0 25.0 False 0 0 \n", + "2 10.0 8.0 3.0 12.0 False 0 0 \n", + "3 7.0 12.0 4.0 20.0 False 0 0 \n", + "4 7.0 10.0 2.0 16.0 True 0 0 \n", + "\n", + " rain thunderstorm \n", + "0 1 1 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 " + ] + }, + "execution_count": 253, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "\n", + "df6.head()" ] }, { @@ -504,7 +2853,41 @@ "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "# Your code here\n", + "df7=df6.copy()\n", + "df7.date=pd.to_datetime(df7.date)" + ] + }, + { + "cell_type": "code", + "execution_count": 274, + "metadata": {}, + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'int' object has no attribute 'toordinal'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[274], line 5\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m## TO DATETIME FUNCIONA POR COLUMNA PERO TOORDINAL\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;66;03m## FUNCIONA LINEA A LINEA, POR ESO LE TENEMOS QUE\u001b[39;00m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m## PASAR UN APPLY LAMBDA\u001b[39;00m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mdatetime\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m datetime\n\u001b[0;32m----> 5\u001b[0m df7\u001b[38;5;241m.\u001b[39mdate\u001b[38;5;241m=\u001b[39mdf7[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: x\u001b[38;5;241m.\u001b[39mtoordinal())\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/series.py:4924\u001b[0m, in \u001b[0;36mSeries.apply\u001b[0;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[1;32m 4789\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[1;32m 4790\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 4791\u001b[0m func: AggFuncType,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 4796\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 4797\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[1;32m 4798\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 4799\u001b[0m \u001b[38;5;124;03m Invoke function on values of Series.\u001b[39;00m\n\u001b[1;32m 4800\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 4915\u001b[0m \u001b[38;5;124;03m dtype: float64\u001b[39;00m\n\u001b[1;32m 4916\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m 4917\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m SeriesApply(\n\u001b[1;32m 4918\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 4919\u001b[0m func,\n\u001b[1;32m 4920\u001b[0m convert_dtype\u001b[38;5;241m=\u001b[39mconvert_dtype,\n\u001b[1;32m 4921\u001b[0m by_row\u001b[38;5;241m=\u001b[39mby_row,\n\u001b[1;32m 4922\u001b[0m args\u001b[38;5;241m=\u001b[39margs,\n\u001b[1;32m 4923\u001b[0m kwargs\u001b[38;5;241m=\u001b[39mkwargs,\n\u001b[0;32m-> 4924\u001b[0m )\u001b[38;5;241m.\u001b[39mapply()\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/apply.py:1427\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1424\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_compat()\n\u001b[1;32m 1426\u001b[0m \u001b[38;5;66;03m# self.func is Callable\u001b[39;00m\n\u001b[0;32m-> 1427\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_standard()\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/apply.py:1507\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1501\u001b[0m \u001b[38;5;66;03m# row-wise access\u001b[39;00m\n\u001b[1;32m 1502\u001b[0m \u001b[38;5;66;03m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[1;32m 1503\u001b[0m \u001b[38;5;66;03m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[1;32m 1504\u001b[0m \u001b[38;5;66;03m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[1;32m 1505\u001b[0m \u001b[38;5;66;03m# Categorical (GH51645).\u001b[39;00m\n\u001b[1;32m 1506\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj\u001b[38;5;241m.\u001b[39mdtype, CategoricalDtype) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1507\u001b[0m mapped \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39m_map_values(\n\u001b[1;32m 1508\u001b[0m mapper\u001b[38;5;241m=\u001b[39mcurried, na_action\u001b[38;5;241m=\u001b[39maction, convert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconvert_dtype\n\u001b[1;32m 1509\u001b[0m )\n\u001b[1;32m 1511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mapped) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(mapped[\u001b[38;5;241m0\u001b[39m], ABCSeries):\n\u001b[1;32m 1512\u001b[0m \u001b[38;5;66;03m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[1;32m 1513\u001b[0m \u001b[38;5;66;03m# See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[1;32m 1514\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_constructor_expanddim(\u001b[38;5;28mlist\u001b[39m(mapped), index\u001b[38;5;241m=\u001b[39mobj\u001b[38;5;241m.\u001b[39mindex)\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[0;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m 918\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[1;32m 919\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mmap(mapper, na_action\u001b[38;5;241m=\u001b[39mna_action)\n\u001b[0;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m algorithms\u001b[38;5;241m.\u001b[39mmap_array(arr, mapper, na_action\u001b[38;5;241m=\u001b[39mna_action, convert\u001b[38;5;241m=\u001b[39mconvert)\n", + "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/pandas/core/algorithms.py:1743\u001b[0m, in \u001b[0;36mmap_array\u001b[0;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m 1741\u001b[0m values \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 1742\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_action \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1743\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer(values, mapper, convert\u001b[38;5;241m=\u001b[39mconvert)\n\u001b[1;32m 1744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1745\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer_mask(\n\u001b[1;32m 1746\u001b[0m values, mapper, mask\u001b[38;5;241m=\u001b[39misna(values)\u001b[38;5;241m.\u001b[39mview(np\u001b[38;5;241m.\u001b[39muint8), convert\u001b[38;5;241m=\u001b[39mconvert\n\u001b[1;32m 1747\u001b[0m )\n", + "File \u001b[0;32mlib.pyx:2972\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n", + "Cell \u001b[0;32mIn[274], line 5\u001b[0m, in \u001b[0;36m\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m## TO DATETIME FUNCIONA POR COLUMNA PERO TOORDINAL\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;66;03m## FUNCIONA LINEA A LINEA, POR ESO LE TENEMOS QUE\u001b[39;00m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m## PASAR UN APPLY LAMBDA\u001b[39;00m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mdatetime\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m datetime\n\u001b[0;32m----> 5\u001b[0m df7\u001b[38;5;241m.\u001b[39mdate\u001b[38;5;241m=\u001b[39mdf7[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: x\u001b[38;5;241m.\u001b[39mtoordinal())\n", + "\u001b[0;31mAttributeError\u001b[0m: 'int' object has no attribute 'toordinal'" + ] + } + ], + "source": [ + "## TO DATETIME FUNCIONA POR COLUMNA PERO TOORDINAL\n", + "## FUNCIONA LINEA A LINEA, POR ESO LE TENEMOS QUE\n", + "## PASAR UN APPLY LAMBDA\n", + "from datetime import datetime\n", + "df7.date=df7['date'].apply(lambda x: x.toordinal())\n" ] }, { @@ -516,11 +2899,248 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 275, "metadata": {}, - "outputs": [], + "outputs": [ + { + "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", + "
datetemphighftempavgftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmphnullsnowfograinthunderstorm
073522374604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0False0011
173522456483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False0000
273522558453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False0000
373522661463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False0000
473522758504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True0000
\n", + "
" + ], + "text/plain": [ + " date temphighf tempavgf templowf dewpointhighf dewpointavgf \\\n", + "0 735223 74 60 45 67.0 49.0 \n", + "1 735224 56 48 39 43.0 36.0 \n", + "2 735225 58 45 32 31.0 27.0 \n", + "3 735226 61 46 31 36.0 28.0 \n", + "4 735227 58 50 41 44.0 40.0 \n", + "\n", + " dewpointlowf humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 43.0 93.0 75.0 57.0 \n", + "1 28.0 93.0 68.0 43.0 \n", + "2 23.0 76.0 52.0 27.0 \n", + "3 21.0 89.0 56.0 22.0 \n", + "4 36.0 86.0 71.0 56.0 \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph null snow fog \\\n", + "0 2.0 20.0 4.0 31.0 False 0 0 \n", + "1 5.0 16.0 6.0 25.0 False 0 0 \n", + "2 10.0 8.0 3.0 12.0 False 0 0 \n", + "3 7.0 12.0 4.0 20.0 False 0 0 \n", + "4 7.0 10.0 2.0 16.0 True 0 0 \n", + "\n", + " rain thunderstorm \n", + "0 1 1 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 " + ] + }, + "execution_count": 275, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "austin_fixed.head(5)" + "\n", + "df7.head()" ] }, { @@ -577,11 +3197,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 293, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "# Your code here:\n", + "y=df7.tempavgf\n", + "X=df7.drop(columns=\"tempavgf\")" ] }, { @@ -593,11 +3215,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 277, "metadata": {}, "outputs": [], "source": [ - "#Your code here:\n" + "# 🤖 Machine Learning\n", + "from sklearn.model_selection import train_test_split # ❗ New" ] }, { @@ -612,11 +3235,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 278, "metadata": {}, "outputs": [], "source": [ - "#Your code here:\n" + "#Your code here:\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" ] }, { @@ -641,11 +3265,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 292, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "1055" + ] + }, + "execution_count": 292, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n" + "# Your code here:\n", + "ts_rows=round(len(df7)/100*80)\n", + "ts_rows" ] }, { @@ -655,35 +3292,923 @@ "Assign the first `ts_rows` rows of `X` to `X_ts_train` and the remaining rows to `X_ts_test`." ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Assign the first `ts_rows` rows of `y` to `y_ts_train` and the remaining rows to `y_ts_test`." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Hay un parámetro en train_test_split que es suffle=False, que si lo ponemos así, impide la randomización de la toma del test y del train. Pero intentaremos hacerlo según aquí se especifica.\n" + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 294, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "# Your code here:\n", + "X_ts_train, X_ts_test, y_ts_train, y_ts_test = train_test_split(X, y, test_size=0.2, shuffle=False)" ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 295, "metadata": {}, + "outputs": [ + { + "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", + "
datetemphighftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmphnullsnowfograinthunderstorm
0735223744567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0False0011
1735224563943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0False0000
2735225583231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0False0000
3735226613136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0False0000
4735227584144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0True0000
........................................................................
1050736273726368.066.059.0100.091.081.030.2730.2230.1410.06.01.07.02.012.0False0010
1051736274765967.060.057.093.085.076.030.1930.1330.0710.010.05.012.02.020.0False0010
1052736275716169.065.061.0100.094.087.030.1430.0930.0410.05.01.07.02.012.0False0010
1053736276696266.064.062.0100.092.084.030.2130.1630.0910.08.02.010.04.016.0False0011
1054736277656062.061.058.0100.094.087.030.2930.2330.1810.06.01.010.06.017.0False0010
\n", + "

1055 rows × 23 columns

\n", + "
" + ], + "text/plain": [ + " date temphighf templowf dewpointhighf dewpointavgf dewpointlowf \\\n", + "0 735223 74 45 67.0 49.0 43.0 \n", + "1 735224 56 39 43.0 36.0 28.0 \n", + "2 735225 58 32 31.0 27.0 23.0 \n", + "3 735226 61 31 36.0 28.0 21.0 \n", + "4 735227 58 41 44.0 40.0 36.0 \n", + "... ... ... ... ... ... ... \n", + "1050 736273 72 63 68.0 66.0 59.0 \n", + "1051 736274 76 59 67.0 60.0 57.0 \n", + "1052 736275 71 61 69.0 65.0 61.0 \n", + "1053 736276 69 62 66.0 64.0 62.0 \n", + "1054 736277 65 60 62.0 61.0 58.0 \n", + "\n", + " humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 93.0 75.0 57.0 \n", + "1 93.0 68.0 43.0 \n", + "2 76.0 52.0 27.0 \n", + "3 89.0 56.0 22.0 \n", + "4 86.0 71.0 56.0 \n", + "... ... ... ... \n", + "1050 100.0 91.0 81.0 \n", + "1051 93.0 85.0 76.0 \n", + "1052 100.0 94.0 87.0 \n", + "1053 100.0 92.0 84.0 \n", + "1054 100.0 94.0 87.0 \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 29.86 29.68 \n", + "1 30.41 30.13 \n", + "2 30.56 30.49 \n", + "3 30.56 30.45 \n", + "4 30.41 30.33 \n", + "... ... ... \n", + "1050 30.27 30.22 \n", + "1051 30.19 30.13 \n", + "1052 30.14 30.09 \n", + "1053 30.21 30.16 \n", + "1054 30.29 30.23 \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 29.59 10.0 7.0 \n", + "1 29.87 10.0 10.0 \n", + "2 30.41 10.0 10.0 \n", + "3 30.30 10.0 10.0 \n", + "4 30.27 10.0 10.0 \n", + "... ... ... ... \n", + "1050 30.14 10.0 6.0 \n", + "1051 30.07 10.0 10.0 \n", + "1052 30.04 10.0 5.0 \n", + "1053 30.09 10.0 8.0 \n", + "1054 30.18 10.0 6.0 \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph null snow \\\n", + "0 2.0 20.0 4.0 31.0 False 0 \n", + "1 5.0 16.0 6.0 25.0 False 0 \n", + "2 10.0 8.0 3.0 12.0 False 0 \n", + "3 7.0 12.0 4.0 20.0 False 0 \n", + "4 7.0 10.0 2.0 16.0 True 0 \n", + "... ... ... ... ... ... ... \n", + "1050 1.0 7.0 2.0 12.0 False 0 \n", + "1051 5.0 12.0 2.0 20.0 False 0 \n", + "1052 1.0 7.0 2.0 12.0 False 0 \n", + "1053 2.0 10.0 4.0 16.0 False 0 \n", + "1054 1.0 10.0 6.0 17.0 False 0 \n", + "\n", + " fog rain thunderstorm \n", + "0 0 1 1 \n", + "1 0 0 0 \n", + "2 0 0 0 \n", + "3 0 0 0 \n", + "4 0 0 0 \n", + "... ... ... ... \n", + "1050 0 1 0 \n", + "1051 0 1 0 \n", + "1052 0 1 0 \n", + "1053 0 1 1 \n", + "1054 0 1 0 \n", + "\n", + "[1055 rows x 23 columns]" + ] + }, + "execution_count": 295, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "Assign the first `ts_rows` rows of `y` to `y_ts_train` and the remaining rows to `y_ts_test`." + "X_ts_train" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 296, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "## Método diana/ fer\n", + "\n", + "X_ts_train_2=X.iloc[:ts_rows]\n", + "X_ts_test_2=X.iloc[ts_rows:]\n", + "y_ts_train_2=y.iloc[:ts_rows]\n", + "y_ts_test_2=y.iloc[ts_rows]" + ] + }, + { + "cell_type": "code", + "execution_count": 297, + "metadata": {}, + "outputs": [ + { + "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", + "
datetemphighftemplowfdewpointhighfdewpointavgfdewpointlowfhumidityhighpercenthumidityavgpercenthumiditylowpercentsealevelpressurehighinchessealevelpressureavginchessealevelpressurelowinchesvisibilityhighmilesvisibilityavgmilesvisibilitylowmileswindhighmphwindavgmphwindgustmphnullsnowfograinthunderstorm
0TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
1TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
2TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
3TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
4TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
........................................................................
1050TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
1051TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
1052TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
1053TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
1054TrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
\n", + "

1055 rows × 23 columns

\n", + "
" + ], + "text/plain": [ + " date temphighf templowf dewpointhighf dewpointavgf dewpointlowf \\\n", + "0 True True True True True True \n", + "1 True True True True True True \n", + "2 True True True True True True \n", + "3 True True True True True True \n", + "4 True True True True True True \n", + "... ... ... ... ... ... ... \n", + "1050 True True True True True True \n", + "1051 True True True True True True \n", + "1052 True True True True True True \n", + "1053 True True True True True True \n", + "1054 True True True True True True \n", + "\n", + " humidityhighpercent humidityavgpercent humiditylowpercent \\\n", + "0 True True True \n", + "1 True True True \n", + "2 True True True \n", + "3 True True True \n", + "4 True True True \n", + "... ... ... ... \n", + "1050 True True True \n", + "1051 True True True \n", + "1052 True True True \n", + "1053 True True True \n", + "1054 True True True \n", + "\n", + " sealevelpressurehighinches sealevelpressureavginches \\\n", + "0 True True \n", + "1 True True \n", + "2 True True \n", + "3 True True \n", + "4 True True \n", + "... ... ... \n", + "1050 True True \n", + "1051 True True \n", + "1052 True True \n", + "1053 True True \n", + "1054 True True \n", + "\n", + " sealevelpressurelowinches visibilityhighmiles visibilityavgmiles \\\n", + "0 True True True \n", + "1 True True True \n", + "2 True True True \n", + "3 True True True \n", + "4 True True True \n", + "... ... ... ... \n", + "1050 True True True \n", + "1051 True True True \n", + "1052 True True True \n", + "1053 True True True \n", + "1054 True True True \n", + "\n", + " visibilitylowmiles windhighmph windavgmph windgustmph null snow \\\n", + "0 True True True True True True \n", + "1 True True True True True True \n", + "2 True True True True True True \n", + "3 True True True True True True \n", + "4 True True True True True True \n", + "... ... ... ... ... ... ... \n", + "1050 True True True True True True \n", + "1051 True True True True True True \n", + "1052 True True True True True True \n", + "1053 True True True True True True \n", + "1054 True True True True True True \n", + "\n", + " fog rain thunderstorm \n", + "0 True True True \n", + "1 True True True \n", + "2 True True True \n", + "3 True True True \n", + "4 True True True \n", + "... ... ... ... \n", + "1050 True True True \n", + "1051 True True True \n", + "1052 True True True \n", + "1053 True True True \n", + "1054 True True True \n", + "\n", + "[1055 rows x 23 columns]" + ] + }, + "execution_count": 297, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X_ts_train==X_ts_train_2" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Hemos comprobado que ambos métodos funcionan bien " ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "base", "language": "python", "name": "python3" }, @@ -697,7 +4222,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.12.2" } }, "nbformat": 4,