-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
executable file
·73 lines (57 loc) · 2.83 KB
/
train.py
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
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
from sklearn.linear_model import LogisticRegression
import argparse
import os
import numpy as np
from sklearn.metrics import mean_squared_error
import joblib
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
import pandas as pd
from azureml.core.run import Run
from azureml.data.dataset_factory import TabularDatasetFactory
def clean_data(data):
# Dict for cleaning data
months = {"jan":1, "feb":2, "mar":3, "apr":4, "may":5, "jun":6, "jul":7, "aug":8, "sep":9, "oct":10, "nov":11, "dec":12}
weekdays = {"mon":1, "tue":2, "wed":3, "thu":4, "fri":5, "sat":6, "sun":7}
# Clean and one hot encode data
x_df = data.to_pandas_dataframe().dropna()
jobs = pd.get_dummies(x_df.job, prefix="job")
x_df.drop("job", inplace=True, axis=1)
x_df = x_df.join(jobs)
x_df["marital"] = x_df.marital.apply(lambda s: 1 if s == "married" else 0)
x_df["default"] = x_df.default.apply(lambda s: 1 if s == "yes" else 0)
x_df["housing"] = x_df.housing.apply(lambda s: 1 if s == "yes" else 0)
x_df["loan"] = x_df.loan.apply(lambda s: 1 if s == "yes" else 0)
contact = pd.get_dummies(x_df.contact, prefix="contact")
x_df.drop("contact", inplace=True, axis=1)
x_df = x_df.join(contact)
education = pd.get_dummies(x_df.education, prefix="education")
x_df.drop("education", inplace=True, axis=1)
x_df = x_df.join(education)
x_df["month"] = x_df.month.map(months)
x_df["day_of_week"] = x_df.day_of_week.map(weekdays)
x_df["poutcome"] = x_df.poutcome.apply(lambda s: 1 if s == "success" else 0)
y_df = x_df.pop("y").apply(lambda s: 1 if s == "yes" else 0)
return x_df, y_df
def main():
# Add arguments to script
parser = argparse.ArgumentParser()
parser.add_argument('--C', type=float, default=1.0, help="Inverse of regularization strength. Smaller values cause stronger regularization")
parser.add_argument('--max_iter', type=int, default=100, help="Maximum number of iterations to converge")
args = parser.parse_args()
run = Run.get_context()
run.log("Regularization Strength:", np.float(args.C))
run.log("Max iterations:", np.int(args.max_iter))
# TODO: Create TabularDataset using TabularDatasetFactory
# Data is located at:
data_link = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
ds = TabularDatasetFactory.from_delimited_files(path=data_link)
x, y = clean_data(ds)
# TODO: Split data into train and test sets.
### YOUR CODE HERE ###a
x_train, x_test, y_train, y_test = train_test_split(x, y, stratify=y, random_state=42)
model = LogisticRegression(C=args.C, max_iter=args.max_iter).fit(x_train, y_train)
accuracy = model.score(x_test, y_test)
run.log("Accuracy", np.float(accuracy))
if __name__ == '__main__':
main()