-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtrain.py
105 lines (78 loc) · 3.67 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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
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
path="https://raw.githubusercontent.com/nsourlos/palda_azure/main/palda.csv"
def clean_data(data):
y_df = data.iloc[:,-2]
x_df = data.iloc[: , :-2] #was -1
# y_df=data.pop('diagnosis')
# rem=data.pop('heal/pat')
# x_df=data
# for i in range(len(x_df)):
# if x_df['diagnosis'].iloc[i]=='peripheral':
# x_df['diagnosis'].iloc[i]=0
# y_df.iloc[i]=0
# elif x_df['diagnosis'].iloc[i]=='central':
# x_df['diagnosis'][i]=1
# y_df.iloc[i]=1
# elif x_df['diagnosis'].iloc[i]=='Healthy':
# x_df['diagnosis'].iloc[i]=3
# y_df.iloc[i]=3
# for i in range(len(y_df)):
# if y_df.iloc[i]=='peripheral':
# y_df.iloc[i]=0
# elif y_df.iloc[i]=='central':
# y_df.iloc[i]=1
# elif y_df.iloc[i]=='Healthy':
# y_df.iloc[i]=3
print(x_df)
print(y_df)
return x_df, y_df
url="https://raw.githubusercontent.com/nsourlos/palda_azure/main/palda.csv"
# ds = TabularDatasetFactory(url)
# ds=from_delimited_files(url, validate=True, include_path=False, infer_column_types=True, set_column_types=None, separator=',', header=True, partition_format=None, support_multi_line=False, empty_as_string=False, encoding='utf8')
ds=TabularDatasetFactory.from_delimited_files(path=url)#datastore_path)
df=ds.to_pandas_dataframe()
### YOUR CODE HERE ###
x, y = clean_data(df)
# 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,test_size=0.2,random_state=42)
run = Run.get_context(allow_offline=True)
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:
# "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
# url="https://raw.githubusercontent.com/nsourlos/palda_azure/main/palda.csv"
# # ds = TabularDatasetFactory(url)
# # ds=from_delimited_files(url, validate=True, include_path=False, infer_column_types=True, set_column_types=None, separator=',', header=True, partition_format=None, support_multi_line=False, empty_as_string=False, encoding='utf8')
# ds=TabularDatasetFactory.from_delimited_files(path=url)#datastore_path)
# df=ds.to_pandas_dataframe()
# ### YOUR CODE HERE ###
# x, y = clean_data(df)
# # 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,test_size=0.2,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))
os.makedirs('outputs', exist_ok=True) #'./'
joblib.dump(model, "./outputs/model.joblib")
if __name__ == '__main__':
main()