Last active
February 24, 2018 20:47
-
-
Save superMDguy/72689a11746079677ddb0d19f26443a1 to your computer and use it in GitHub Desktop.
Adds weather data to dataset for kaggle "Recruit Restaurant Visitor Forecasting" competition
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train.visit_date = pd.to_datetime(train.visit_date) | |
test.visit_date = pd.to_datetime(test.visit_date) | |
def add_weather(dataset): | |
print('Adding weather...') | |
air_nearest = pd.read_csv( | |
'../../data/raw/weather/air_store_info_with_nearest_active_station.csv') | |
unique_air_store_ids = list(dataset.air_store_id.unique()) | |
weather_dir = '../../data/raw/weather/1-1-16_5-31-17_Weather/' | |
weather_keep_columns = ['precipitation', 'avg_temperature'] | |
dataset_with_weather = dataset.copy() | |
for column in weather_keep_columns: | |
dataset_with_weather[column] = np.nan | |
for air_id in unique_air_store_ids: | |
station = air_nearest[air_nearest.air_store_id == air_id].station_id.iloc[0] | |
weather_data = pd.read_csv(weather_dir + station + '.csv', parse_dates=['calendar_date']).rename(columns={'calendar_date': 'visit_date'}) | |
this_store = dataset.air_store_id == air_id | |
merged = dataset[this_store].merge(weather_data, on='visit_date', how='left') | |
for column in weather_keep_columns: | |
dataset_with_weather.loc[this_store, column] = merged[column] | |
return dataset_with_weather | |
train = add_weather(train) | |
test = add_weather(test) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment