-
Notifications
You must be signed in to change notification settings - Fork 0
/
training.py
44 lines (36 loc) · 1.64 KB
/
training.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
from flask import Flask, session, jsonify, request
import pandas as pd
import numpy as np
import pickle
from joblib import dump
import os
from sklearn import metrics
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import json
from features import preprocess_data
#Load config.json and get path variables
with open('config.json','r') as f:
config = json.load(f)
dataset_csv_path = os.path.join(config['output_folder_path'])
model_path = os.path.join(config['output_model_path'])
def train_model():
"""Function for training the model"""
df = pd.read_csv(os.path.join(dataset_csv_path, "finaldata.csv"))
df_x, df_y, encoder = preprocess_data(df, None)
x_train, x_test, y_train, y_test = train_test_split(df_x, df_y, test_size=0.20)
model = LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=100,
multi_class='ovr', n_jobs=None, penalty='l2',
random_state=0, solver='liblinear', tol=0.0001, verbose=0,
warm_start=False)
#fit the logistic regression to your data
model.fit(x_train, y_train)
print(model.score(x_train, y_train))
print(model.score(x_test, y_test))
#write the trained model and encoder to your workspace in a file called trainedmodel.pkl
#write the trained model to your workspace in a file called trainedmodel.pkl
dump(model, os.path.join(model_path, "trainedmodel.pkl"))
dump(encoder, os.path.join(model_path, "encoder.pkl"))
if __name__ == "__main__":
train_model()