xgb.py 文件源码

def preprocess(file,istrian):
    df=pd.read_csv(file,parse_dates=['Date'],dayfirst=True)
    end_missing=['Average_Atmospheric_Pressure','Max_Atmospheric_Pressure',
    'Min_Atmospheric_Pressure','Min_Ambient_Pollution','Max_Ambient_Pollution']
    df=df.fillna(-1)
    if istrian:
        outcome=df.Footfall
        df=df.drop(['Footfall'],axis=1)
    else:
        outcome=np.nan

    df['month']=df['Date'].apply(lambda x: x.month)
    df['date']=df['Date'].apply(lambda x: x.day)
    df['weekday']=df['Date'].apply(lambda x: x.weekday())
    df['sardiya']=df['month'].apply(lambda x: 1 if x in [1,2,11,12,3] else 0)
    df.date=df.date.apply(get_normal_date)
    dummies=pd.get_dummies(df.Park_ID,prefix='park')
    dummies=pd.get_dummies(df.Location_Type,prefix='location')
    df['Direction_Of_Wind2']=df.Direction_Of_Wind.apply(get_wind_dir)

    return df,outcome

#load training set