FilesExpand file tree

master

/

train.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

32 lines (26 loc) · 886 Bytes

master

/

train.py

Copy path

Top

File metadata and controls

• Code
• Blame

32 lines (26 loc) · 886 Bytes

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

26

27

28

29

30

31

32

import feast

from joblib import dump

import pandas as pd

from sklearn.linear_model import LinearRegression

# Load driver order data

orders = pd.read_csv("driver_orders.csv", sep="\t")

orders["event_timestamp"] = pd.to_datetime(orders["event_timestamp"])

# Connect to your local feature store

fs = feast.FeatureStore(repo_path="driver_ranking/")

# Retrieve training data from BigQuery

training_df = fs.get_historical_features(

entity_df=orders,

feature_refs=[

"driver_hourly_stats:conv_rate",

"driver_hourly_stats:acc_rate",

"driver_hourly_stats:avg_daily_trips",

],

).to_df()

# Train model

target = "trip_completed"

reg = LinearRegression()

train_X = training_df[training_df.columns.drop(target).drop("event_timestamp")]

train_Y = training_df.loc[:, target]

reg.fit(train_X[sorted(train_X)], train_Y)

# Save model

dump(reg, "driver_model.bin")