Skip to content

Instantly share code, notes, and snippets.

@aishwarya-singh25

aishwarya-singh25/changing_dtype.py

Last active December 7, 2019 09:57
Show Gist options
  • Save aishwarya-singh25/4e7c163911a4b43bb9a3606d1ba994a1 to your computer and use it in GitHub Desktop.
Save aishwarya-singh25/4e7c163911a4b43bb9a3606d1ba994a1 to your computer and use it in GitHub Desktop.
Download ZIP
Time Series Features
Raw
changing_dtype.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data.dtypes
Raw
date_features.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['year']=data['Datetime'].dt.year
data['month']=data['Datetime'].dt.month
data['day']=data['Datetime'].dt.day
data['dayofweek_num']=data['Datetime'].dt.dayofweek
data['dayofweek_name']=data['Datetime'].dt.weekday_name
data.head()
Raw
expanding_window.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['expanding_mean'] = data['Count'].expanding(2).mean()
data = data[['Datetime','Count', 'expanding_mean']]
data.head(10)
Raw
lag_feature.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['lag_1'] = data['Count'].shift(1)
data = data[['Datetime', 'lag_1', 'Count']]
data.head()
Raw
lag_seven.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['lag_1'] = data['Count'].shift(1)
data['lag_2'] = data['Count'].shift(2)
data['lag_3'] = data['Count'].shift(3)
data['lag_4'] = data['Count'].shift(4)
data['lag_5'] = data['Count'].shift(5)
data['lag_6'] = data['Count'].shift(6)
data['lag_7'] = data['Count'].shift(7)
data = data[['Datetime', 'lag_1', 'lag_2', 'lag_3', 'lag_4', 'lag_5', 'lag_6', 'lag_7', 'Count']]
data.head(10)
Raw
loading_data.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data.dtypes
Raw
rolling_mean.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['rolling_mean'] = data['Count'].rolling(window=7).mean()
data = data[['Datetime', 'rolling_mean', 'Count']]
data.head(10)
Raw
time_features.py
import pandas as pd
data = pd.read_csv('Train_SU63ISt.csv')
data['Datetime'] = pd.to_datetime(data['Datetime'],format='%d-%m-%Y %H:%M')
data['Hour'] = data['Datetime'].dt.hour
data['minute'] = data['Datetime'].dt.minute
data.head()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment