logi.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
diabetes = pd.read_csv('dia.csv')
print(diabetes.columns)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(diabetes.loc[:, diabetes.columns != 'Outcome'], diabetes['Outcome'], stratify=diabetes['Outcome'], random_state=66)
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression().fit(X_train, y_train)
print("Training set score: {:.3f}".format(logreg.score(X_train, y_train)))
print("Test set score: {:.3f}".format(logreg.score(X_test, y_test)))
diabetes_features = [x for i,x in enumerate(diabetes.columns) if i!=8]
plt.figure(figsize=(8,3))
#plt.plot(logreg.coef_.T, 'o', label="C=1")
plt.plot(logreg.coef_.T, '^', label="C=100")
#plt.plot(logreg.coef_.T, 'v', label="C=0.001")
plt.xticks(range(diabetes.shape[1]), diabetes_features, rotation=90)
plt.hlines(0, 0, diabetes.shape[1])
plt.ylim(-5, 5)
plt.xlabel("Feature")
plt.ylabel("Coefficient magnitude")
plt.legend()
#plt.savefig('log_coef')