diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 68b3762..00e6cd4 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -12,11 +12,14 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ - "#Import your libraries\n" + "from sklearn.datasets import load_iris\n", + "import numpy as np\n", + "import pandas as pd\n", + "import seaborn as sns\n" ] }, { @@ -38,11 +41,168 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 2, + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercent...SeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEvents
02013-12-21746045674943937557...29.6829.591072204310.46Rain , Thunderstorm
12013-12-22564839433628936843...30.1329.8710105166250
22013-12-23584532312723765227...30.4930.4110101083120
\n", + "

3 rows × 21 columns

\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", + "\n", + " DewPointLowF HumidityHighPercent HumidityAvgPercent HumidityLowPercent ... \\\n", + "0 43 93 75 57 ... \n", + "1 28 93 68 43 ... \n", + "2 23 76 52 27 ... \n", + "\n", + " SeaLevelPressureAvgInches SeaLevelPressureLowInches VisibilityHighMiles \\\n", + "0 29.68 29.59 10 \n", + "1 30.13 29.87 10 \n", + "2 30.49 30.41 10 \n", + "\n", + " VisibilityAvgMiles VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH \\\n", + "0 7 2 20 4 31 \n", + "1 10 5 16 6 25 \n", + "2 10 10 8 3 12 \n", + "\n", + " PrecipitationSumInches Events \n", + "0 0.46 Rain , Thunderstorm \n", + "1 0 \n", + "2 0 \n", + "\n", + "[3 rows x 21 columns]" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin=pd.read_csv(\"austin_weather.csv\")\n", + "austin.head(3)" ] }, { @@ -57,29 +217,396 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 3, + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercent...SeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEvents
02013-12-21746045674943937557...29.6829.591072204310.46Rain , Thunderstorm
12013-12-22564839433628936843...30.1329.8710105166250
22013-12-23584532312723765227...30.4930.4110101083120
32013-12-24614631362821895622...30.4530.310107124200
42013-12-25585041444036867156...30.3330.271010710216T
\n", + "

5 rows × 21 columns

\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", + " SeaLevelPressureAvgInches SeaLevelPressureLowInches VisibilityHighMiles \\\n", + "0 29.68 29.59 10 \n", + "1 30.13 29.87 10 \n", + "2 30.49 30.41 10 \n", + "3 30.45 30.3 10 \n", + "4 30.33 30.27 10 \n", + "\n", + " VisibilityAvgMiles VisibilityLowMiles WindHighMPH WindAvgMPH WindGustMPH \\\n", + "0 7 2 20 4 31 \n", + "1 10 5 16 6 25 \n", + "2 10 10 8 3 12 \n", + "3 10 7 12 4 20 \n", + "4 10 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 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin.head(5)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array(['Rain , Thunderstorm', ' ', 'Rain', 'Fog', 'Rain , Snow',\n", + " 'Fog , Rain', 'Thunderstorm', 'Fog , Rain , Thunderstorm',\n", + " 'Fog , Thunderstorm'], dtype=object)" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "austin[\"Events\"].unique()" ] }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 5, + "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 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": [ + "austin.info()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "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", + "
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": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin.describe()\n" ] }, { @@ -113,20 +640,37 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 7, + "metadata": {}, + "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": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin[\"DewPointAvgF\"].unique()\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ - "# Your observation here\n" + "# it became an object because we have 1 string between a column, \"-\".\n" ] }, { @@ -140,7 +684,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -151,14 +695,282 @@ " 'WindGustMPH', 'PrecipitationSumInches']" ] }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 1319 entries, 0 to 1318\n", + "Data columns (total 16 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 DewPointHighF 1312 non-null float64\n", + " 1 DewPointAvgF 1312 non-null float64\n", + " 2 DewPointLowF 1312 non-null float64\n", + " 3 HumidityHighPercent 1317 non-null float64\n", + " 4 HumidityAvgPercent 1317 non-null float64\n", + " 5 HumidityLowPercent 1317 non-null float64\n", + " 6 SeaLevelPressureHighInches 1316 non-null float64\n", + " 7 SeaLevelPressureAvgInches 1316 non-null float64\n", + " 8 SeaLevelPressureLowInches 1316 non-null float64\n", + " 9 VisibilityHighMiles 1307 non-null float64\n", + " 10 VisibilityAvgMiles 1307 non-null float64\n", + " 11 VisibilityLowMiles 1307 non-null float64\n", + " 12 WindHighMPH 1317 non-null float64\n", + " 13 WindAvgMPH 1317 non-null float64\n", + " 14 WindGustMPH 1315 non-null float64\n", + " 15 PrecipitationSumInches 1195 non-null float64\n", + "dtypes: float64(16)\n", + "memory usage: 165.0 KB\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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercent...SeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHPrecipitationSumInchesEvents
02013-12-2174604567.049.043.093.075.057.0...29.6829.5910.07.02.020.04.031.00.46Rain , Thunderstorm
12013-12-2256483943.036.028.093.068.043.0...30.1329.8710.010.05.016.06.025.00.00
22013-12-2358453231.027.023.076.052.027.0...30.4930.4110.010.010.08.03.012.00.00
32013-12-2461463136.028.021.089.056.022.0...30.4530.3010.010.07.012.04.020.00.00
42013-12-2558504144.040.036.086.071.056.0...30.3330.2710.010.07.010.02.016.0NaN
\n", + "

5 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", + " 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", + " ... 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", + " VisibilityHighMiles VisibilityAvgMiles VisibilityLowMiles WindHighMPH \\\n", + "0 10.0 7.0 2.0 20.0 \n", + "1 10.0 10.0 5.0 16.0 \n", + "2 10.0 10.0 10.0 8.0 \n", + "3 10.0 10.0 7.0 12.0 \n", + "4 10.0 10.0 7.0 10.0 \n", + "\n", + " WindAvgMPH WindGustMPH PrecipitationSumInches Events \n", + "0 4.0 31.0 0.46 Rain , Thunderstorm \n", + "1 6.0 25.0 0.00 \n", + "2 3.0 12.0 0.00 \n", + "3 4.0 20.0 0.00 \n", + "4 2.0 16.0 NaN \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "array([49., 36., 27., 28., 40., 39., 41., 26., 42., 22., 48., 32., 8.,\n", + " 11., 45., 55., 61., 37., 47., 25., 23., 20., 33., 30., 29., 17.,\n", + " 14., 13., 54., 59., 15., 24., 34., 35., 57., 50., 53., 60., 46.,\n", + " 56., 51., 31., 38., 62., 43., 63., 64., 67., 66., 58., 70., 68.,\n", + " 65., 69., 71., 72., nan, 73., 74., 21., 44., 52., 12., 75., 76.,\n", + " 18.])" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin_2 = austin[wrong_type_columns].apply(pd.to_numeric, errors='coerce')\n", + "austin_2.info()\n", + "austin[wrong_type_columns]=austin_2\n", + "display(austin.head(5))\n", + "austin[\"DewPointAvgF\"].unique()" + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], - "source": [ - "# Your code here\n" - ] + "source": [] }, { "cell_type": "markdown", @@ -169,11 +981,63 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 11, + "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" + ] + }, + { + "data": { + "text/plain": [ + "array([49., 36., 27., 28., 40., 39., 41., 26., 42., 22., 48., 32., 8.,\n", + " 11., 45., 55., 61., 37., 47., 25., 23., 20., 33., 30., 29., 17.,\n", + " 14., 13., 54., 59., 15., 24., 34., 35., 57., 50., 53., 60., 46.,\n", + " 56., 51., 31., 38., 62., 43., 63., 64., 67., 66., 58., 70., 68.,\n", + " 65., 69., 71., 72., nan, 73., 74., 21., 44., 52., 12., 75., 76.,\n", + " 18.])" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin.head(5)\n", + "austin.info()\n", + "austin[\"DewPointAvgF\"].unique()" ] }, { @@ -200,11 +1064,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "missing_values=austin[austin.isnull().any(axis=1)]" ] }, { @@ -233,11 +1097,73 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Date 1319\n", + "TempHighF 1319\n", + "TempAvgF 1319\n", + "TempLowF 1319\n", + "DewPointHighF 1312\n", + "DewPointAvgF 1312\n", + "DewPointLowF 1312\n", + "HumidityHighPercent 1317\n", + "HumidityAvgPercent 1317\n", + "HumidityLowPercent 1317\n", + "SeaLevelPressureHighInches 1316\n", + "SeaLevelPressureAvgInches 1316\n", + "SeaLevelPressureLowInches 1316\n", + "VisibilityHighMiles 1307\n", + "VisibilityAvgMiles 1307\n", + "VisibilityLowMiles 1307\n", + "WindHighMPH 1317\n", + "WindAvgMPH 1317\n", + "WindGustMPH 1315\n", + "PrecipitationSumInches 1195\n", + "Events 1319\n", + "dtype: int64" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "Date 136\n", + "TempHighF 136\n", + "TempAvgF 136\n", + "TempLowF 136\n", + "DewPointHighF 129\n", + "DewPointAvgF 129\n", + "DewPointLowF 129\n", + "HumidityHighPercent 134\n", + "HumidityAvgPercent 134\n", + "HumidityLowPercent 134\n", + "SeaLevelPressureHighInches 133\n", + "SeaLevelPressureAvgInches 133\n", + "SeaLevelPressureLowInches 133\n", + "VisibilityHighMiles 124\n", + "VisibilityAvgMiles 124\n", + "VisibilityLowMiles 124\n", + "WindHighMPH 134\n", + "WindAvgMPH 134\n", + "WindGustMPH 132\n", + "PrecipitationSumInches 12\n", + "Events 136\n", + "dtype: int64" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display(austin.count())\n", + "display(missing_values.count())\n" ] }, { @@ -249,11 +1175,23 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.10310841546626232" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "\n", + "len(missing_values)/len(austin)" ] }, { @@ -267,11 +1205,44 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 15, + "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", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "# Your code here\n", + "austin.isna().sum()" ] }, { @@ -283,11 +1254,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.10310841546626232" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "len(missing_values[\"PrecipitationSumInches\"])/len(austin)" ] }, { @@ -309,16 +1291,232 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, "outputs": [], "source": [ - "# Your code here \n", - "\n", - "\n", - "# Print `austin` to confirm the column is indeed removed\n", - "\n", - "austin" + "austin.drop(columns=[\"PrecipitationSumInches\"], inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercentSeaLevelPressureHighInchesSeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHEvents
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0Rain , Thunderstorm
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0
\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 \n", + "0 Rain , Thunderstorm \n", + "1 \n", + "2 \n", + "3 \n", + "4 " + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin.head()" ] }, { @@ -336,11 +1534,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "austin_fixed=austin.interpolate(inplace=False)" ] }, { @@ -352,11 +1550,43 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 35, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Date 0\n", + "TempHighF 0\n", + "TempAvgF 0\n", + "TempLowF 0\n", + "DewPointHighF 0\n", + "DewPointAvgF 0\n", + "DewPointLowF 0\n", + "HumidityHighPercent 0\n", + "HumidityAvgPercent 0\n", + "HumidityLowPercent 0\n", + "SeaLevelPressureHighInches 0\n", + "SeaLevelPressureAvgInches 0\n", + "SeaLevelPressureLowInches 0\n", + "VisibilityHighMiles 0\n", + "VisibilityAvgMiles 0\n", + "VisibilityLowMiles 0\n", + "WindHighMPH 0\n", + "WindAvgMPH 0\n", + "WindGustMPH 0\n", + "Events 0\n", + "dtype: int64" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin_fixed.isna().sum()\n", + "austin.isna().sum()" ] }, { @@ -377,11 +1607,32 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here:\n" + "execution_count": 38, + "metadata": {}, + "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": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin_fixed[\"Events\"].value_counts()\n" ] }, { @@ -395,11 +1646,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": {}, "outputs": [], "source": [ - "# Your answer:\n" + "# rain\n" ] }, { @@ -415,18 +1666,250 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "ename": "KeyError", + "evalue": "\"['event'] not found in axis\"", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[44], line 9\u001b[0m\n\u001b[0;32m 7\u001b[0m austin_fixed\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevent_fog\u001b[39m\u001b[38;5;124m\"\u001b[39m], inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 8\u001b[0m austin_fixed\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevent_thunderstorm\u001b[39m\u001b[38;5;124m\"\u001b[39m] , inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m----> 9\u001b[0m austin_fixed\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevent\u001b[39m\u001b[38;5;124m\"\u001b[39m], inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 13\u001b[0m \u001b[38;5;66;03m# Print your new dataframe to check whether new columns have been created:\u001b[39;00m\n\u001b[0;32m 15\u001b[0m austin_fixed\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\frame.py:5258\u001b[0m, in \u001b[0;36mDataFrame.drop\u001b[1;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[0;32m 5110\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdrop\u001b[39m(\n\u001b[0;32m 5111\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 5112\u001b[0m labels: IndexLabel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 5119\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[0;32m 5120\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[0;32m 5121\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 5122\u001b[0m \u001b[38;5;124;03m Drop specified labels from rows or columns.\u001b[39;00m\n\u001b[0;32m 5123\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 5256\u001b[0m \u001b[38;5;124;03m weight 1.0 0.8\u001b[39;00m\n\u001b[0;32m 5257\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m-> 5258\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mdrop(\n\u001b[0;32m 5259\u001b[0m labels\u001b[38;5;241m=\u001b[39mlabels,\n\u001b[0;32m 5260\u001b[0m axis\u001b[38;5;241m=\u001b[39maxis,\n\u001b[0;32m 5261\u001b[0m index\u001b[38;5;241m=\u001b[39mindex,\n\u001b[0;32m 5262\u001b[0m columns\u001b[38;5;241m=\u001b[39mcolumns,\n\u001b[0;32m 5263\u001b[0m level\u001b[38;5;241m=\u001b[39mlevel,\n\u001b[0;32m 5264\u001b[0m inplace\u001b[38;5;241m=\u001b[39minplace,\n\u001b[0;32m 5265\u001b[0m errors\u001b[38;5;241m=\u001b[39merrors,\n\u001b[0;32m 5266\u001b[0m )\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\generic.py:4549\u001b[0m, in \u001b[0;36mNDFrame.drop\u001b[1;34m(self, labels, axis, index, columns, level, inplace, errors)\u001b[0m\n\u001b[0;32m 4547\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[0;32m 4548\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[1;32m-> 4549\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[0;32m 4551\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inplace:\n\u001b[0;32m 4552\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_update_inplace(obj)\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\generic.py:4591\u001b[0m, in \u001b[0;36mNDFrame._drop_axis\u001b[1;34m(self, labels, axis, level, errors, only_slice)\u001b[0m\n\u001b[0;32m 4589\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[0;32m 4590\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 4591\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[0;32m 4592\u001b[0m indexer \u001b[38;5;241m=\u001b[39m axis\u001b[38;5;241m.\u001b[39mget_indexer(new_axis)\n\u001b[0;32m 4594\u001b[0m \u001b[38;5;66;03m# Case for non-unique axis\u001b[39;00m\n\u001b[0;32m 4595\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\indexes\\base.py:6699\u001b[0m, in \u001b[0;36mIndex.drop\u001b[1;34m(self, labels, errors)\u001b[0m\n\u001b[0;32m 6697\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mask\u001b[38;5;241m.\u001b[39many():\n\u001b[0;32m 6698\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[1;32m-> 6699\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;00m\u001b[38;5;28mlist\u001b[39m(labels[mask])\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[0;32m 6700\u001b[0m indexer \u001b[38;5;241m=\u001b[39m indexer[\u001b[38;5;241m~\u001b[39mmask]\n\u001b[0;32m 6701\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[1;31mKeyError\u001b[0m: \"['event'] not found in axis\"" + ] + } + ], "source": [ "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", + " austin_fixed[event]=0\n", + " \n", + "austin_fixed.drop(columns=[\"event_rain\"], inplace=True)\n", + "austin_fixed.drop(columns=[\"event_snow\"], inplace=True)\n", + "austin_fixed.drop(columns=[\"event_fog\"], inplace=True)\n", + "austin_fixed.drop(columns=[\"event_thunderstorm\"] , inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercent...VisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHEventsSnowFogRainThunderstorm
02013-12-2174604567.049.043.093.075.057.0...7.02.020.04.031.0Rain , Thunderstorm0000
12013-12-2256483943.036.028.093.068.043.0...10.05.016.06.025.00000
22013-12-2358453231.027.023.076.052.027.0...10.010.08.03.012.00000
32013-12-2461463136.028.021.089.056.022.0...10.07.012.04.020.00000
42013-12-2558504144.040.036.086.071.056.0...10.07.010.02.016.00000
\n", + "

5 rows × 24 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", + " 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", + " ... VisibilityAvgMiles VisibilityLowMiles WindHighMPH WindAvgMPH \\\n", + "0 ... 7.0 2.0 20.0 4.0 \n", + "1 ... 10.0 5.0 16.0 6.0 \n", + "2 ... 10.0 10.0 8.0 3.0 \n", + "3 ... 10.0 7.0 12.0 4.0 \n", + "4 ... 10.0 7.0 10.0 2.0 \n", + "\n", + " WindGustMPH Events Snow Fog Rain Thunderstorm \n", + "0 31.0 Rain , Thunderstorm 0 0 0 0 \n", + "1 25.0 0 0 0 0 \n", + "2 12.0 0 0 0 0 \n", + "3 20.0 0 0 0 0 \n", + "4 16.0 0 0 0 0 \n", + "\n", + "[5 rows x 24 columns]" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "austin_fixed.head()" ] }, { @@ -446,11 +1929,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 51, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "event_list = ['Snow', 'Fog', 'Rain', 'Thunderstorm']\n", + "\n", + "# Loop over the events and create the corresponding columns\n", + "for event in event_list:\n", + " austin_fixed[event] = austin_fixed[\"Events\"].str.contains(event).astype(int)" ] }, { @@ -462,11 +1949,26 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Fog\n", + "0 1250\n", + "1 69\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here\n" + "austin_fixed.head(5)\n", + "austin_fixed[\"Fog\"].value_counts()" ] }, { @@ -478,11 +1980,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, "outputs": [], "source": [ - "# Your code here\n" + "austin_fixed.drop(columns=[\"Events\"], inplace=True)\n" ] }, { @@ -500,27 +2002,258 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" + "execution_count": 66, + "metadata": {}, + "outputs": [ + { + "ename": "TypeError", + "evalue": "strptime() argument 1 must be str, not int", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[66], line 3\u001b[0m\n\u001b[0;32m 1\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[1;32m----> 3\u001b[0m austin_fixed[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDate\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m austin_fixed[\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: datetime\u001b[38;5;241m.\u001b[39mstrptime(x, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mY-\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mm-\u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mtoordinal())\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\series.py:4630\u001b[0m, in \u001b[0;36mSeries.apply\u001b[1;34m(self, func, convert_dtype, args, **kwargs)\u001b[0m\n\u001b[0;32m 4520\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[0;32m 4521\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 4522\u001b[0m func: AggFuncType,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 4525\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m 4526\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[0;32m 4527\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 4528\u001b[0m \u001b[38;5;124;03m Invoke function on values of Series.\u001b[39;00m\n\u001b[0;32m 4529\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 4628\u001b[0m \u001b[38;5;124;03m dtype: float64\u001b[39;00m\n\u001b[0;32m 4629\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m-> 4630\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m SeriesApply(\u001b[38;5;28mself\u001b[39m, func, convert_dtype, args, kwargs)\u001b[38;5;241m.\u001b[39mapply()\n", + "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\apply.py:1025\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1022\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_str()\n\u001b[0;32m 1024\u001b[0m \u001b[38;5;66;03m# self.f is Callable\u001b[39;00m\n\u001b[1;32m-> 1025\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[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\apply.py:1076\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1074\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 1075\u001b[0m values \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m)\u001b[38;5;241m.\u001b[39m_values\n\u001b[1;32m-> 1076\u001b[0m mapped \u001b[38;5;241m=\u001b[39m lib\u001b[38;5;241m.\u001b[39mmap_infer(\n\u001b[0;32m 1077\u001b[0m values,\n\u001b[0;32m 1078\u001b[0m f,\n\u001b[0;32m 1079\u001b[0m convert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconvert_dtype,\n\u001b[0;32m 1080\u001b[0m )\n\u001b[0;32m 1082\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[0;32m 1083\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[0;32m 1084\u001b[0m \u001b[38;5;66;03m# See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[0;32m 1085\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[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\_libs\\lib.pyx:2834\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[1;34m()\u001b[0m\n", + "Cell \u001b[1;32mIn[66], line 3\u001b[0m, in \u001b[0;36m\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m 1\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[1;32m----> 3\u001b[0m austin_fixed[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDate\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m austin_fixed[\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: datetime\u001b[38;5;241m.\u001b[39mstrptime(x, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mY-\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mm-\u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mtoordinal())\n", + "\u001b[1;31mTypeError\u001b[0m: strptime() argument 1 must be str, not int" + ] + } + ], + "source": [ + "from datetime import datetime\n", + "\n", + "austin_fixed[\"Date\"] = austin_fixed[\"Date\"].apply(lambda x: datetime.strptime(x, \"%Y-%m-%d\").toordinal())" ] }, { - "cell_type": "markdown", - "metadata": {}, + "cell_type": "code", + "execution_count": 70, + "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", + "
DateTempHighFTempAvgFTempLowFDewPointHighFDewPointAvgFDewPointLowFHumidityHighPercentHumidityAvgPercentHumidityLowPercentSeaLevelPressureHighInchesSeaLevelPressureAvgInchesSeaLevelPressureLowInchesVisibilityHighMilesVisibilityAvgMilesVisibilityLowMilesWindHighMPHWindAvgMPHWindGustMPHEvents
02013-12-2174604567.049.043.093.075.057.029.8629.6829.5910.07.02.020.04.031.0Rain , Thunderstorm
12013-12-2256483943.036.028.093.068.043.030.4130.1329.8710.010.05.016.06.025.0
22013-12-2358453231.027.023.076.052.027.030.5630.4930.4110.010.010.08.03.012.0
32013-12-2461463136.028.021.089.056.022.030.5630.4530.3010.010.07.012.04.020.0
42013-12-2558504144.040.036.086.071.056.030.4130.3330.2710.010.07.010.02.016.0
\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 \n", + "0 Rain , Thunderstorm \n", + "1 \n", + "2 \n", + "3 \n", + "4 " + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "#### Print `austin_fixed` to check your `Date` column." + "austin_fixed.head(5)" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], "source": [ - "austin_fixed.head(5)" + "#### Print `austin_fixed` to check your `Date` column." ] }, { @@ -577,11 +2310,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 72, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "# Your code here:\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "X=austin_fixed.drop(columns=[\"TempAvgF\"]) \n", + "y= austin_fixed[\"TempAvgF\"] " ] }, { @@ -593,7 +2330,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, "outputs": [], "source": [ @@ -612,11 +2349,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 73, "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=0.20, random_state=0)" ] }, { @@ -641,7 +2379,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, "outputs": [], "source": [ @@ -657,7 +2395,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": {}, "outputs": [], "source": [ @@ -673,7 +2411,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, "outputs": [], "source": [ @@ -683,7 +2421,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -697,7 +2435,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.11.5" } }, "nbformat": 4,