{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":61145,"databundleVersionId":7047669,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Applications","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"This notebook has to be created through the competition","metadata":{}},{"cell_type":"markdown","source":"## Table of Contents\n* [Read data](#Read-data)\n* [Data pre-processing](#Data-pre-processing)\n* [Map of all weather stations that measure air temperature](#Map-of-all-weather-stations-that-measure-air-temperature)\n* [What's next?](#What's-next)","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport plotly.graph_objects as go\nimport math","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:56:30.632441Z","iopub.execute_input":"2024-03-13T14:56:30.632742Z","iopub.status.idle":"2024-03-13T14:56:32.964078Z","shell.execute_reply.started":"2024-03-13T14:56:30.632710Z","shell.execute_reply":"2024-03-13T14:56:32.963091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Read data","metadata":{}},{"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/cool-quiet-city-competition/cozie_responses_and_physiological_data_training.csv', index_col=[0], \n                       keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], \n                       date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_solution = pd.read_csv('/kaggle/input/cool-quiet-city-competition/cozie_responses_and_physiological_data_test_public.csv', index_col=[0],\n                          keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], \n                          date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_rain = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_rainfall.csv', parse_dates=True, index_col=[0])\ndf_temperature = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_air-temperature.csv', parse_dates=True, index_col=[0])\ndf_humidity = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_relative-humidity.csv', parse_dates=True, index_col=[0])\ndf_wind_speed = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_wind-speed.csv', parse_dates=True, index_col=[0])\ndf_wind_direction = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_wind-direction.csv', parse_dates=True, index_col=[0])\ndf_stations = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_stations.csv').drop(columns=['Unnamed: 0'])","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:56:32.965928Z","iopub.execute_input":"2024-03-13T14:56:32.966571Z","iopub.status.idle":"2024-03-13T14:58:32.055691Z","shell.execute_reply.started":"2024-03-13T14:56:32.966538Z","shell.execute_reply":"2024-03-13T14:58:32.054412Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_stations.info()","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.061447Z","iopub.execute_input":"2024-03-13T14:58:32.061724Z","iopub.status.idle":"2024-03-13T14:58:32.082928Z","shell.execute_reply.started":"2024-03-13T14:58:32.061699Z","shell.execute_reply":"2024-03-13T14:58:32.081842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Data pre-processing\n\n### Check dates\n\nWhen checking the last date of different kinds of dataframes it becomes clear that the watch survey responses only last until Jan 21, 2023, while the weather data lasts until July 3, 2023.","metadata":{}},{"cell_type":"code","source":"print(df_train.index.max())\nprint(df_solution.index.max())\nprint(df_rain.index.max())","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.084254Z","iopub.execute_input":"2024-03-13T14:58:32.084568Z","iopub.status.idle":"2024-03-13T14:58:32.103393Z","shell.execute_reply.started":"2024-03-13T14:58:32.084541Z","shell.execute_reply":"2024-03-13T14:58:32.102408Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We don't really need the weather data after Jan 21, 2023, so we might just as well get rid of it.","metadata":{}},{"cell_type":"code","source":"df_rain = df_rain[df_rain.index<'2023-01-22']\ndf_temperature = df_temperature[df_temperature.index<'2023-01-22']\ndf_humidity = df_humidity[df_humidity.index<'2023-01-22']\ndf_wind_speed = df_wind_speed[df_wind_speed.index<'2023-01-22']\ndf_wind_direction = df_wind_direction[df_wind_direction.index<'2023-01-22']","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.104585Z","iopub.execute_input":"2024-03-13T14:58:32.104863Z","iopub.status.idle":"2024-03-13T14:58:32.141598Z","shell.execute_reply.started":"2024-03-13T14:58:32.104839Z","shell.execute_reply":"2024-03-13T14:58:32.140878Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Check weather data","metadata":{}},{"cell_type":"code","source":"# Show new shortened air temperature dataframe\ndf_temperature.describe()","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.142544Z","iopub.execute_input":"2024-03-13T14:58:32.142864Z","iopub.status.idle":"2024-03-13T14:58:32.276600Z","shell.execute_reply.started":"2024-03-13T14:58:32.142835Z","shell.execute_reply":"2024-03-13T14:58:32.275523Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"It looks like there is no temperature data available in before Jan 21, 2023 for weather station S117. So, we might just as well remove that column","metadata":{}},{"cell_type":"code","source":"df_temperature = df_temperature.drop(columns=['S117'])\n# Get dimensions of the air temperature data\ndf_temperature.shape","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.277745Z","iopub.execute_input":"2024-03-13T14:58:32.278020Z","iopub.status.idle":"2024-03-13T14:58:32.288337Z","shell.execute_reply.started":"2024-03-13T14:58:32.277996Z","shell.execute_reply":"2024-03-13T14:58:32.287095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The weather dataframes are rather large. This can make the plotting of the data slow and the output images large. To make it a bit lighter, we are going to resample the data hourly.","metadata":{"execution":{"iopub.status.busy":"2024-03-12T21:09:04.412698Z","iopub.execute_input":"2024-03-12T21:09:04.413286Z","iopub.status.idle":"2024-03-12T21:09:04.419237Z","shell.execute_reply.started":"2024-03-12T21:09:04.413253Z","shell.execute_reply":"2024-03-12T21:09:04.41811Z"}}},{"cell_type":"code","source":"# Resample weather data\ndf_temperature_average = df_temperature.resample('60min').mean()\ndf_rain_sum = df_rain.resample('60min').sum() # note: for rain the data is aggregated with a sum instead of the mean\ndf_humidity_average = df_humidity.resample('60min').mean()\ndf_wind_speed_average = df_wind_speed.resample('60min').mean()\ndf_wind_direction_average = df_wind_direction.resample('60min').mean()\n\n# Check size of resulting dataframe\ndf_temperature_average.shape","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.289876Z","iopub.execute_input":"2024-03-13T14:58:32.290154Z","iopub.status.idle":"2024-03-13T14:58:32.374257Z","shell.execute_reply.started":"2024-03-13T14:58:32.290129Z","shell.execute_reply":"2024-03-13T14:58:32.373326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Map watch survey questions to question ID\n","metadata":{}},{"cell_type":"code","source":"ws_questions = {\"q_noise_nearby\": \"Noise distractions nearby? (without earphones)\",\n                \"q_noise_kind\": \"What kind of noise?\",\n                \"q_earphones\": \"Wearing earphones?\",\n                \"q_thermal_preference\": \"Thermally, what do you prefer now?\",\n                \"q_location\": \"Where are you?\",\n                \"q_location_office\": \"What kind of office?\",\n                \"q_location_transport\": \"What kind of transport?\",\n                \"q_alone_group\": \"Alone or in a group?\",\n                \"q_activity_category_alone\": \"Category of activity? (alone)\",\n                \"q_activity_category_group\": \"Category of activity? (group)\"}","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:58:32.378070Z","iopub.execute_input":"2024-03-13T14:58:32.378374Z","iopub.status.idle":"2024-03-13T14:58:32.383443Z","shell.execute_reply.started":"2024-03-13T14:58:32.378336Z","shell.execute_reply":"2024-03-13T14:58:32.382513Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plot weather data\n\n### Plot weather weather data time-series¶\n\nBelow we are going to plot the air temperature data from all weather stations. I used the Matplotlib method plt.plot() instead of sns.lineplot(). The reason is that plt.plot() shows the gaps in the data, while sns.lineplot() draws straight lines accross the gaps.\n","metadata":{}},{"cell_type":"code","source":"cols_num = 1\nrows_num = len(df_temperature_average.columns)\ncol_current = 0\nrow_current = 0 \nfig, axs = plt.subplots(rows_num, cols_num, figsize=(20,3*rows_num))\nplt.subplots_adjust(hspace = 0.5)\n\nfor i, col in enumerate(df_temperature_average.columns):\n    row_current = i\n    axs[row_current].plot(df_temperature_average.index, df_temperature_average[col])\n    station_name = df_stations[df_stations['id']==col]['name'].values[0]\n    axs[row_current].set_title(f'Weather Station {col}: {station_name}')\n    axs[row_current].set_ylabel('Air Temperature [°C]')","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:19.595810Z","iopub.execute_input":"2024-03-13T14:59:19.596119Z","iopub.status.idle":"2024-03-13T14:59:25.376624Z","shell.execute_reply.started":"2024-03-13T14:59:19.596092Z","shell.execute_reply":"2024-03-13T14:59:25.374486Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Since, we are going to plot more weather data, we might just as well wrap the above code for plotting in to a function.","metadata":{}},{"cell_type":"code","source":"# Function that plots weather data fromm all weather stations\ndef plot_weather(df, ylabel):\n    cols_num = 1\n    rows_num = len(df.columns)\n    col_current = 0\n    row_current = 0 \n    fig, axs = plt.subplots(rows_num, cols_num, figsize=(20,3*rows_num))\n    plt.subplots_adjust(hspace = 0.5)\n\n    for i, col in enumerate(df.columns):\n        row_current = i\n        axs[row_current].plot(df.index, df[col])\n        station_name = df_stations[df_stations['id']==col]['name'].values[0]\n        axs[row_current].set_title(f'Weather Station {col}: {station_name}')\n        axs[row_current].set_ylabel(ylabel)\n    \n    return fig, axs","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:31.370924Z","iopub.execute_input":"2024-03-13T14:59:31.371263Z","iopub.status.idle":"2024-03-13T14:59:31.378871Z","shell.execute_reply.started":"2024-03-13T14:59:31.371237Z","shell.execute_reply":"2024-03-13T14:59:31.377772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Temperature","metadata":{}},{"cell_type":"code","source":"fig, axs = plot_weather(df_temperature_average, 'Temperature [°C]')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Rainfall","metadata":{}},{"cell_type":"code","source":"fig, axs = plot_weather(df_rain_sum, 'Rainfall [mm/h]')","metadata":{"execution":{"iopub.status.idle":"2024-03-13T14:59:07.807399Z","shell.execute_reply.started":"2024-03-13T14:58:44.068591Z","shell.execute_reply":"2024-03-13T14:59:07.806410Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Relative humidity","metadata":{}},{"cell_type":"code","source":"fig, axs = plot_weather(df_humidity_average, 'Relative humidity [%]')\n","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:07.808635Z","iopub.execute_input":"2024-03-13T14:59:07.808970Z","iopub.status.idle":"2024-03-13T14:59:13.340942Z","shell.execute_reply.started":"2024-03-13T14:59:07.808928Z","shell.execute_reply":"2024-03-13T14:59:13.339630Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Map of all weather stations that measure air temperature","metadata":{}},{"cell_type":"code","source":"# Have a look at the weather station meta data\ndf_stations.head()","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:13.342223Z","iopub.execute_input":"2024-03-13T14:59:13.342578Z","iopub.status.idle":"2024-03-13T14:59:13.355347Z","shell.execute_reply.started":"2024-03-13T14:59:13.342549Z","shell.execute_reply":"2024-03-13T14:59:13.354481Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_stations.shape","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:13.356683Z","iopub.execute_input":"2024-03-13T14:59:13.357173Z","iopub.status.idle":"2024-03-13T14:59:13.367942Z","shell.execute_reply.started":"2024-03-13T14:59:13.357140Z","shell.execute_reply":"2024-03-13T14:59:13.367054Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Have a look at the air temperature data\ndf_temperature.columns","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:13.369470Z","iopub.execute_input":"2024-03-13T14:59:13.369918Z","iopub.status.idle":"2024-03-13T14:59:13.377797Z","shell.execute_reply.started":"2024-03-13T14:59:13.369873Z","shell.execute_reply":"2024-03-13T14:59:13.376851Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Note, the list of all weather stations is much longer then the list with weather stations that can measure air temperature. Hence, we need to pre-process the data a bit and only pick the weather stations that can measure temperature data.","metadata":{}},{"cell_type":"code","source":"# Initialize a new dataframe for creating the map\ndf_map = pd.DataFrame(columns=['latitude', 'longitude', 'text'])\n\n\n# Go through each column of the temperature dataframe\nfor col in df_temperature.columns:\n    # Get the weather station name based on the station id\n    station_name = df_stations.loc[df_stations.id==col].name.values[0]\n    \n    # Create a new row, with latitude, longitude, hover text, and marker color as columns\n    df_row = pd.DataFrame([{'latitude': df_stations.loc[df_stations.id==col].latitude.values[0], \n                            'longitude': df_stations.loc[df_stations.id==col].longitude.values[0], \n                            'text': f'Station ID: {col} <br>Station name: {station_name} <br>Measurement: Rain',\n                            'color': 'rgb(0, 128, 255)'}])\n    \n    # Append new row to map dataframe\n    df_map = pd.concat([df_map, df_row])\n    \ndf_map.head()","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:13.379053Z","iopub.execute_input":"2024-03-13T14:59:13.379348Z","iopub.status.idle":"2024-03-13T14:59:13.437120Z","shell.execute_reply.started":"2024-03-13T14:59:13.379324Z","shell.execute_reply":"2024-03-13T14:59:13.436069Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The pre-processing for the maps is done. Now, we can go and actually create the map chart.","metadata":{}},{"cell_type":"code","source":"# Create trace and add markers to map\ntrace = go.Scattermapbox(lat=df_map.latitude, \n                         lon=df_map.longitude,\n                         mode='markers',\n                         marker=dict(size=10,\n                                     color=df_map['color'],\n                                     opacity=0.8),\n                         hovertemplate = \"\",\n                         text=df_map['text'])\n\n# Define the layout for the map\nlayout = go.Layout(\n    margin={\"l\": 0, \"r\": 0, \"t\": 0, \"b\": 0},\n    mapbox=dict(\n        style='carto-positron', # Alternative: 'open-street-map',\n        center=dict(lat=df_map.latitude.median(),\n                    lon=df_map.longitude.median()),\n        zoom=10,\n        ),\n    height=700, width=900)\n\n# Create figure\nfig = go.Figure(data=[trace], layout=layout)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2024-03-13T14:59:13.438441Z","iopub.execute_input":"2024-03-13T14:59:13.438731Z","iopub.status.idle":"2024-03-13T14:59:13.856605Z","shell.execute_reply.started":"2024-03-13T14:59:13.438704Z","shell.execute_reply":"2024-03-13T14:59:13.855439Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Note, you can hovering the cursor over the markers will reveal some meta information about the weather station.","metadata":{}},{"cell_type":"markdown","source":"## What's next?","metadata":{}},{"cell_type":"markdown","source":"How do I continue this? Where to start?!\n\nGO TO THE COMPETITION SITE!\n\n[https://www.kaggle.com/competitions/cool-quiet-city-competition](https://www.kaggle.com/competitions/cool-quiet-city-competition)","metadata":{}},{"cell_type":"markdown","source":"# First place code in the competition","metadata":{}},{"cell_type":"code","source":"# Import necessary libraries\nimport pandas as pd \nimport numpy as np\nfrom datetime import datetime, timedelta\nfrom sklearn.metrics import accuracy_score, f1_score\nfrom sklearn.metrics import confusion_matrix\nfrom math import cos, asin, sqrt, pi\nfrom sklearn.feature_selection import SelectFromModel\nfrom sklearn.experimental import enable_iterative_imputer\nfrom sklearn.impute import IterativeImputer\nfrom sklearn.model_selection import StratifiedKFold\nimport lightgbm as lgb\nfrom catboost import CatBoostClassifier\nfrom xgboost import XGBClassifier\n\npd.set_option('display.max_columns', None)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Read data\nRead all csv file into dataframes.","metadata":{}},{"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/cool-quiet-city-competition/cozie_responses_and_physiological_data_training.csv', index_col=[0], keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_solution = pd.read_csv('/kaggle/input/cool-quiet-city-competition/cozie_responses_and_physiological_data_test_public.csv', index_col=[0], keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_stations = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_stations.csv').drop(columns=['Unnamed: 0'])\ndf_rain = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_rainfall.csv', parse_dates=True, index_col=[0])\ndf_temperature = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_air-temperature.csv', parse_dates=True, index_col=[0])\ndf_humidity = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_relative-humidity.csv', parse_dates=True, index_col=[0])\ndf_wind_speed = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_wind-speed.csv', parse_dates=True, index_col=[0])\ndf_wind_direction = pd.read_csv('/kaggle/input/cool-quiet-city-competition/weather_wind-direction.csv', parse_dates=True, index_col=[0])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature Engineering (Part 1)","metadata":{}},{"cell_type":"markdown","source":"Create dataframes for the wind direction sine and cosine","metadata":{}},{"cell_type":"code","source":"df_wind_direction_sin = df_wind_direction.copy(deep=True)\ndf_wind_direction_cos = df_wind_direction.copy(deep=True)\nfor s in df_wind_direction.columns:\n    df_wind_direction_sin[s] = np.sin(np.pi/180*df_wind_direction_sin[s])\n    df_wind_direction_cos[s] = np.cos(np.pi/180*df_wind_direction_cos[s])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Merge train and test data in a single dataframe","metadata":{}},{"cell_type":"code","source":"df_train['source']='train'\ndf_solution['source']='solution'\ndf_all = pd.concat([df_train, df_solution])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"One hot encoding for categorical features, and dropping the categorical variables","metadata":{}},{"cell_type":"code","source":"df_all['q_Indoor'] = df_all['q_location'].str.contains(\"Indoor\")\ndf_all['q_Class'] = df_all['q_location'].isin(['Indoor - Class'])\ndf_all['q_Home'] = df_all['q_location'].isin(['Indoor - Home'])\ndf_all['q_Office'] = df_all['q_location'].isin(['Indoor - Office'])\ndf_all['q_Indoor_Other'] = df_all['q_location'].isin(['Indoor - Other'])\ndf_all['q_Outdoor'] = df_all['q_location'].isin(['Outdoor'])\ndf_all['q_Transportation'] = df_all['q_location'].isin(['Transportation'])\ndf_all['q_alone_group'] = df_all['q_alone_group'].isin(['Alone'])\ndf_all['q_Bus'] = df_all['q_location_transport'].isin(['Bus'])\ndf_all['q_Car'] = df_all['q_location_transport'].isin(['Car'])\ndf_all['q_Taxi'] = df_all['q_location_transport'].isin(['Taxi'])\ndf_all['q_Train'] = df_all['q_location_transport'].isin(['Train'])\ndf_all['q_Transport_Other'] = df_all['q_location_transport'].isin(['Other'])\ndf_all['q_Focus'] = df_all['q_activity_category_alone'].isin(['Focus'])\ndf_all['q_Leisure'] = df_all['q_activity_category_alone'].isin(['Leisure'])\ndf_all['q_Alone_Activity_Other'] = df_all['q_activity_category_alone'].isin(['Other'])\ndf_all['q_Collaborate'] = df_all['q_activity_category_group'].isin(['Collaborate'])\ndf_all['q_Learn'] = df_all['q_activity_category_group'].isin(['Learn'])\ndf_all['q_Socialize'] = df_all['q_activity_category_group'].isin(['Socialize'])\ndf_all['q_Group_Activity_Other'] = df_all['q_activity_category_group'].isin(['Other'])\ndf_all['q_Conference room'] = df_all['q_location_office'].isin(['Conference room'])\ndf_all['q_Cubicles'] = df_all['q_location_office'].isin(['Cubicles'])\ndf_all['q_Individual'] = df_all['q_location_office'].isin(['Individual'])\ndf_all['q_Large open plan'] = df_all['q_location_office'].isin(['Large open plan'])\ndf_all['q_Not applicable'] = df_all['q_location_office'].isin(['Not applicable'])\ndf_all['q_Small shared'] = df_all['q_location_office'].isin(['Small shared'])\n\ndf_all = df_all.drop(columns=['q_location','q_location_transport','q_activity_category_alone','q_activity_category_group','q_location_office'])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\"Duration\" feature represent the log of the time needed to complete the survey, and it's defined as the log of the difference between the time where the survey was submitted and the time where the survey started","metadata":{}},{"cell_type":"code","source":"df_all['duration'] = np.log((df_all.index - df_all['ws_timestamp_start']).dt.total_seconds())","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Compute day and time features","metadata":{}},{"cell_type":"code","source":"df_all['time_of_day_cos'] = np.cos(np.deg2rad((df_all.index.hour*60 + df_all.index.minute)/4))\ndf_all['time_of_day_sin'] = np.sin(np.deg2rad((df_all.index.hour*60 + df_all.index.minute)/4))\ndf_all['time_of_day'] = (df_all.index.hour*60 + df_all.index.minute)\ndf_all['day_of_week'] = df_all.index.dayofweek\n#df_all = df_all.reset_index()\n#df_all = df_all.sort_values(['id_participant', 'time'])\n#df_all = df_all.set_index('time', drop=True)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Compute aggregates to the features provided by Apple HealthKit","metadata":{}},{"cell_type":"code","source":"df_all['med_resting_heart_rate'] = df_all.groupby('id_participant')['ts_resting_heart_rate'].transform('median')\ndf_all['med_audio_exposure_environment'] = df_all.groupby('id_participant')['ts_audio_exposure_environment'].transform('median')\ndf_all['med_oxygen_saturation'] = df_all.groupby('id_participant')['ts_oxygen_saturation'].transform('median')\ndf_all['med_stand_time'] = df_all.groupby('id_participant')['ts_stand_time'].transform('median')\ndf_all['med_heart_rate'] = df_all.groupby('id_participant')['ts_heart_rate'].transform('median')\ndf_all['med_step_count'] = df_all.groupby('id_participant')['ts_step_count'].transform('median')\ndf_all['med_walking_distance'] = df_all.groupby('id_participant')['ts_walking_distance'].transform('median')\n\ndf_all['mean_resting_heart_rate'] = df_all.groupby('id_participant')['ts_resting_heart_rate'].transform('mean')\ndf_all['mean_audio_exposure_environment'] = df_all.groupby('id_participant')['ts_audio_exposure_environment'].transform('mean')\ndf_all['mean_oxygen_saturation'] = df_all.groupby('id_participant')['ts_oxygen_saturation'].transform('mean')\ndf_all['mean_stand_time'] = df_all.groupby('id_participant')['ts_stand_time'].transform('mean')\ndf_all['mean_heart_rate'] = df_all.groupby('id_participant')['ts_heart_rate'].transform('mean')\ndf_all['mean_step_count'] = df_all.groupby('id_participant')['ts_step_count'].transform('mean')\ndf_all['mean_walking_distance'] = df_all.groupby('id_participant')['ts_walking_distance'].transform('mean')\n\ndf_all['std_resting_heart_rate'] = df_all.groupby('id_participant')['ts_resting_heart_rate'].transform('std')\ndf_all['std_audio_exposure_environment'] = df_all.groupby('id_participant')['ts_audio_exposure_environment'].transform('std')\ndf_all['std_oxygen_saturation'] = df_all.groupby('id_participant')['ts_oxygen_saturation'].transform('std')\ndf_all['std_stand_time'] = df_all.groupby('id_participant')['ts_stand_time'].transform('std')\ndf_all['std_heart_rate'] = df_all.groupby('id_participant')['ts_heart_rate'].transform('std')\ndf_all['std_step_count'] = df_all.groupby('id_participant')['ts_step_count'].transform('std')\ndf_all['std_walking_distance'] = df_all.groupby('id_participant')['ts_walking_distance'].transform('std')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Normalize all the features to have uniform scale","metadata":{}},{"cell_type":"code","source":"df_all['ts_resting_heart_rate'] = (df_all['ts_resting_heart_rate'] - df_all['mean_resting_heart_rate'])/df_all['std_resting_heart_rate']\ndf_all['ts_audio_exposure_environment'] = (df_all['ts_audio_exposure_environment'] - df_all['mean_audio_exposure_environment'])/df_all['std_audio_exposure_environment']\ndf_all['ts_oxygen_saturation'] = (df_all['ts_oxygen_saturation'] - df_all['mean_oxygen_saturation'])/df_all['std_oxygen_saturation']\ndf_all['ts_stand_time'] = (df_all['ts_stand_time'] - df_all['mean_stand_time'])/df_all['std_stand_time']\ndf_all['ts_heart_rate'] = (df_all['ts_heart_rate'] - df_all['mean_heart_rate'])/df_all['std_heart_rate']\ndf_all['ts_step_count'] = (df_all['ts_step_count'] - df_all['mean_step_count'])/df_all['std_step_count']\ndf_all['ts_walking_distance'] = (df_all['ts_walking_distance'] - df_all['mean_walking_distance'])/df_all['std_walking_distance']","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Interpolate the features provided by Apple HealthKit\nHealth data, e.g., ts_heart_reate, and the watch survey responses, e.g., q_thermal_preference, do not have coinciding timestamps. Hence, the health data needs to be interpolated at the timestamps of the watch survey responses.\n\nThe interpolated values are stored in columns with the prefix ws_ which stands for 'watch survey', e.g., the interpolated values of ts_heart_rate are stored in ws_heart_rate.","metadata":{}},{"cell_type":"code","source":"# Function to resample health data at the timestamps of watch survey responses.\ndef resample_health(df, col_name, col_name_new):\n    df[col_name_new] = df[col_name].interpolate(method='linear').bfill().ffill().mask(df['ws_survey_count'].isna())\n    return df","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Resample normalized health data\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_heart_rate', col_name_new='ws_heart_rate').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_audio_exposure_environment', col_name_new='ws_audio_exposure_environment').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_oxygen_saturation', col_name_new='ws_oxygen_saturation').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_resting_heart_rate', col_name_new='ws_resting_heart_rate').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_stand_time', col_name_new='ws_stand_time').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_step_count', col_name_new='ws_step_count').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_walking_distance', col_name_new='ws_walking_distance').reset_index(level=[0], drop=True)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Interpolate weather data\nThe weather data is distributed over several dataframes. Each measurement, e.g., rain or air temperature, is in a separate dataframe. The column names are the IDs of the weather stations. There is one dataframe (df_stations), which contains meta information to the weather stations, e.g., coordinates and names.\n\nTo make the weather data usable, we need to find the nearest weather stations for each watch survey response in df_all. Then we can transfer the measurement values with the same timestamp to from the weather data dataframe, e.g., df_rain, to the dataframe with the Cozie data (df_all).","metadata":{}},{"cell_type":"code","source":"# Function to get weather data for a given timestamp and location from the nearest weather station\ndef get_weather_data(df_weather_data, lat, lon, timestamp):    \n    # Get timestamp with no seconds or microseconds\n    timestamp = timestamp.replace(second=0, microsecond=0)\n    \n    # Get weather data for timestamp above\n    weather_data_row = df_weather_data[(df_weather_data.index >= timestamp- timedelta(hours=0, minutes=10)) & (df_weather_data.index <= timestamp + timedelta(hours=0, minutes=10))]\n\n    # If no weather data is available for timestamp above, get weather data for next minute\n    if (weather_data_row.empty):\n        timestamp = timestamp + pd.Timedelta(minutes=1)\n        weather_data_row = df_weather_data[df_weather_data.index == timestamp]\n        # If there is still no weather data available, return NaN\n        if (weather_data_row.empty):\n            timestamp = timestamp - 2 * pd.Timedelta(minutes=1)\n            weather_data_row = df_weather_data[df_weather_data.index == timestamp]\n            if (weather_data_row.empty):\n                return np.NaN\n\n    # Get weather station ids from weather stations with with data\n    station_ids_with_data = weather_data_row.columns[weather_data_row.count() > 0].tolist()\n\n    # Get weather stations with data\n    df_stations2 = df_stations[df_stations.id.isin(station_ids_with_data)]\n\n    # Compute distance to each weather station\n    df_stations2['distance'] = df_stations2.apply(lambda x: distance(x['latitude'], x['longitude'], lat, lon), axis=1)\n\n    # Get nearest weather station\n    station_id_nearest = df_stations2[df_stations2.distance==df_stations2.distance.min()].id.values[0]\n\n    # Retrun NaN for cases where the nearest weather station is more than 10km away\n    if df_stations2.distance.min()>10:\n        return np.NaN\n\n    # Return weather data from nearest weather station\n    return np.nanmean(weather_data_row[station_id_nearest])\n\n# Function to compute distnace on spherical earth\ndef distance(lat1, lon1, lat2, lon2):\n    r = 6371 # km\n    p = pi / 180\n\n    a = 0.5 - cos((lat2-lat1)*p)/2 + cos(lat1*p) * cos(lat2*p) * (1-cos((lon2-lon1)*p))/2\n    return 2 * r * asin(sqrt(a))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Apply above function to the dataset for all weather data\ndf_all = df_all.reset_index()\ndf_all['ws_rainfall'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_rain, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all['ws_air_temperature'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_temperature, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all['ws_relative_humidity'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_humidity, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all['ws_wind_speed'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_wind_speed, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all['ws_wind_direction_sin'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_wind_direction_sin, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all['ws_wind_direction_cos'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_wind_direction_cos, row['ws_latitude'], row['ws_longitude'], row['time']), axis=1)\ndf_all = df_all.set_index('time', drop=True)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Remove unused rows and columns ","metadata":{}},{"cell_type":"code","source":"# Remove all rows that are not a watch surve response\ndf_all = df_all[df_all.ws_survey_count.notna()]\n\n# Remove some timestamp columns\ndf_all = df_all.drop(columns=['ws_timestamp_location', 'ws_timestamp_start'])\n\n# Remove columns of the original health data those are no longer needed since we are going to use the interpolated values\ndf_all = df_all.drop(columns=['ts_heart_rate',\n                              'ts_audio_exposure_environment',\n                              'ts_oxygen_saturation',\n                              'ts_resting_heart_rate',\n                              'ts_stand_time', \n                              'ts_step_count',\n                              'ts_walking_distance'])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature Engineering (Part 2)\nThe computation of these features is faster after we have dropped lots of survery rows","metadata":{}},{"cell_type":"markdown","source":"\"own_earphone\" and \"own_noise_cancelling\" noise cancelling are two features that represent whether a user actually own an earphone or a noise cancelling headset, this information is infered by the user previous answers","metadata":{}},{"cell_type":"code","source":"earphone_dict = df_all.groupby(['id_participant','q_earphones'])['duration'].count().to_dict()\ndf_all['own_earphones'] = 0\ndf_all['own_noise_cancelling'] = 0\nfor index, row in df_all.iterrows():\n    if (row['id_participant'], 'Earphones') in earphone_dict:\n        df_all.at[index, 'own_earphones'] = 1\n    if (row['id_participant'], 'Noise cancelling') in earphone_dict:\n        df_all.at[index, 'own_noise_cancelling'] = 1","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Update the features \"own_earphone\" and \"own_noise_cancelling\" by the fact that nobody uses noise cancelling in class since it defies the purpose of going to class, and the users who haven't used earphones in class, they won't start doing that","metadata":{}},{"cell_type":"code","source":"Use_earphone_in_class = set(df_all[(df_all['q_Class']) & (df_all['q_earphones']=='Earphones')]['id_participant'].unique())\nbeen_to_class = set(df_all[(df_all['q_Class'])&(df_all['source'] == 'train')]['id_participant'].unique())\ndiff = been_to_class.difference(Use_earphone_in_class)\nfor index, row in df_all.iterrows():\n    if row['q_Class']:\n        df_all.at[index, 'own_noise_cancelling'] = 0\n        if row['id_participant'] in diff:\n            df_all.at[index, 'own_earphones'] = 0","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Count how many times a location was used in the dataset\ndf_all['location_count'] = 0\nfor index, row in df_all.iterrows():\n    df_all.at[index, 'location_count'] = len(df_all[(df_all['ws_latitude'] == row['ws_latitude']) & (df_all['ws_longitude'] == row['ws_longitude'])])\n\n#calculate the portion of time a user answer a survery from a specific location\ndf_all['location_prob'] = 0\nfor index, row in df_all.iterrows():\n    temp = df_all[(df_all['id_participant']==row['id_participant']) & (df_all['ws_latitude'] == row['ws_latitude']) & (df_all['ws_longitude'] == row['ws_longitude'])]\n    prob = len(temp) / len(df_all[(df_all['id_participant']==row['id_participant'])])\n    df_all.at[index, 'location_prob'] = prob","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Split data\nWe split the data into the training set and solution set according to the original data","metadata":{}},{"cell_type":"code","source":"# Separte training and solution data again\ndf_train = df_all[df_all.source == 'train'].copy()\ndf_solution = df_all[df_all.source == 'solution'].copy()\n\n# Drop the helper columns ws_surve_count_2 and source again\ndf_train = df_train.drop(columns=['source'])\ndf_solution = df_solution.drop(columns=['source'])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Data preparation\nFor the machine learning model below, all input and output values need to be numeric. At this point, the watch survey the response columns, e.g., q_noise_nearby, are of type string. Hence, we need convert the values in these columns into numbers.","metadata":{}},{"cell_type":"code","source":"# Find columns with values that are not numeric\ncat_vars = list(df_train.select_dtypes(include=['object']).columns)\n# encoding categorical variables\ndict_cat = {}\n\nfor var in cat_vars:\n    if var == 'id_participant': # no need to encode the participant ID\n        continue\n    # convert categorical variables into 'category' type\n    df_train[var] = df_train[var].astype('category')\n    df_solution[var] = df_solution[var].astype('category')\n    \n    # dictionary to keep track of the variable mapping: {variable-name: {number1: string1, number2: string2, ...}\n    dict_cat[var] = dict(enumerate(df_train[var].cat.categories))\n\n    # encode variables, missing values are encoded as -1\n    df_train[var] = df_train[var].cat.codes\n    df_solution[var] = df_solution[var].cat.codes","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Predict any column\nWe are going to wrap up above code into a function in order to make the prediction of the other columns a bit more convenient. The steps are mostly the same as above and might feel a bit repetitive.","metadata":{}},{"cell_type":"code","source":"from sklearn.pipeline import Pipeline, make_pipeline\nfrom sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, BaggingClassifier\nfrom sklearn.ensemble import VotingClassifier, StackingClassifier","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def predict_any_column(column_name, df_all, df_solution):\n    # Remove rows where the predicting variable is missing\n    df_all = df_all[df_all[column_name] != -1]\n    \n    # Remove rows where the predicting variable is missing\n    df_all = df_all.drop(columns=['id_participant'])\n    df_solution = df_solution.drop(columns=['id_participant'])\n    \n    # Count classes in predicting variable\n    num_class = df_train[column_name].unique()\n    \n    # Break dataframe into variables and ground truth\n    y_all = df_all[column_name].to_numpy()\n    X_all = df_all.drop(['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference'], axis=1)#.to_numpy()\n    cat_features = [f for f in cat_vars if f in X_all.columns]\n    X_all2 = X_all.to_numpy()\n    X_solution = df_solution.drop(['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference'], axis=1)\n    X_solution2 = X_solution.to_numpy()\n    # Select features\n    #sel = SelectFromModel(XGBClassifier(num_class=num_class, objective='multi:softmax', enable_categorical=False))\n    #sel.fit(X_all,y_all)\n    #selected_feat= X_all.columns[(sel.get_support())]\n    arr = np.zeros((len(num_class),len(num_class)))\n    score = 0\n    print(num_class)\n    y_solution = np.zeros(shape=(X_solution.shape[0],len(num_class)))\n    y_train = np.zeros(shape=(X_all.shape[0],len(num_class)))\n    skf = StratifiedKFold(n_splits=5,random_state=1990,shuffle=True)\n    for i, (train_index, test_index) in enumerate(skf.split(X_all, y_all)):\n        # Initialize model\n        models = [          \n           ('catBoost',make_pipeline(CatBoostClassifier(iterations=1000, verbose=1000, random_seed=42,learning_rate=0.05))),          \n           ('lgbm',make_pipeline(lgb.LGBMClassifier(random_state=42))),   \n           ('XGB',make_pipeline(XGBClassifier(objective='multi:softmax',random_state=42)))     \n        ]\n        voter = VotingClassifier(models, voting = 'soft')\n        # Predict and evaluate\n        voter.fit(X_all.iloc[train_index], y_all[train_index])\n        y_pred = voter.predict_proba(X_all.iloc[test_index]) \n        \n        score += accuracy_score(y_all[test_index], np.argmax(y_pred, axis=1))/5\n        arr = arr + confusion_matrix(y_all[test_index], np.argmax(y_pred, axis=1))\n\n        # Predict solution\n        y_solution += voter.predict_proba(X_solution) #+ clf2.predict_proba(X_solution2)\n    \n    print('Model accuracy score: {0:0.4f}'. format(score))\n    #print(arr)\n    \n    return np.argmax(y_solution, axis=1)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create a copy of the solution dataframe for submission\ndf_submission = df_solution.copy()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Predictions\n* q_noise_nearby\n* q_noise_kind\n* q_earphones\n* q_thermal_preference","metadata":{}},{"cell_type":"code","source":"df_submission['q_noise_nearby'] = predict_any_column('q_noise_nearby', df_train, df_solution)\ndf_submission['q_noise_kind'] = predict_any_column('q_noise_kind', df_train, df_solution)\ndf_submission['q_earphones'] = predict_any_column('q_earphones', df_train, df_solution)\ndf_submission['q_thermal_preference'] = predict_any_column('q_thermal_preference', df_train, df_solution)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Perform some postprocesiing\nThe labels were predicted independently, so, some combinations of the labels might not be possible, so this sample code try to fix few of these labels","metadata":{}},{"cell_type":"code","source":"# Convert classes back form integers to strings\nfor key in dict_cat:\n    if key in df_solution.columns and key in ['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference']:\n        df_submission[key] = df_submission[key].replace(dict_cat[key])\n# Select only necessary columns for submission\nsub = df_submission[['id_unique', 'q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference']].set_index('id_unique')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Do a little bit of post processing\nfor index, row in sub.iterrows():\n    if row['q_noise_nearby'] == 'A little' and row['q_noise_kind'] == 'Not applicable' and row['q_earphones'] == 'Not applicable':\n        sub.at[index, 'q_earphones'] = 'No earphones'","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Create submission file","metadata":{}},{"cell_type":"code","source":"# Write dataframe to csv file\nsub.to_csv('submission.csv')","metadata":{},"execution_count":null,"outputs":[]}]}