-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpredict.py
More file actions
25 lines (20 loc) · 1.08 KB
/
predict.py
File metadata and controls
25 lines (20 loc) · 1.08 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
import pandas as pd
import numpy as np
def predict(input_df,filename='output.csv'):
#input_df = pd.concat([p.get_arrival_date(), p.get_is_canceled(), p.get_adr(), p.get_number_of_days()], axis=1)
input_df['is_canceled'] = input_df['is_canceled'] * (-1) + 1
input_df['total_adr'] = input_df['is_canceled'] * input_df['adr']* input_df['number_of_days']
input_df = input_df[['arrival_date','total_adr']]
input_df = input_df.groupby('arrival_date').sum()
input_df['label'] = (input_df['total_adr'] / 10000).astype(int)
input_df = input_df[['label']]
input_df.to_csv(filename)
def predict_ensemble(input_df):
#input_df = pd.concat([p.get_arrival_date(), p.get_is_canceled(), p.get_adr(), p.get_number_of_days()], axis=1)
input_df['is_canceled'] = input_df['is_canceled'] * (-1) + 1
input_df['total_adr'] = input_df['is_canceled'] * input_df['adr']* input_df['number_of_days']
input_df = input_df[['arrival_date','total_adr']]
input_df = input_df.groupby('arrival_date').sum()
input_df['label'] = (input_df['total_adr'] / 10000).astype(int)
input_df = input_df[['label']]
return input_df