Session4.py

############## Classification#############
###########Logistic Regression
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression

X, y = load_iris(return_X_y=True)

###### Devide data to test and train
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)

logreg = LogisticRegression(random_state=0, solver='lbfgs', multi_class='multinomial')
logregmodel = logreg.fit(X_train, y_train)

y_pred = logregmodel.predict(X_test)
# array([0, 0])
print(logregmodel.predict_proba(X_test))
# array([[9.8...e-01, 1.8...e-02, 1.4...e-08], [9.7...e-01, 2.8...e-02, ...e-08]])
logesticRscore = logregmodel.score(X_test, y_test)

########Confusion matrix
from sklearn import metrics
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
print(cnf_matrix)

######ploting
# import required modules
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
#matplotlib inline
class_names=[0,1] # name  of classes
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)

# create heatmap
sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')

plt.show()

#####Metrics
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
# print("Precision:",metrics.precision_score(y_test, y_pred))
# print("Recall:",metrics.recall_score(y_test, y_pred))

#### Roc Curve
y_pred_proba = logreg.predict_proba(X_test)[::,1]
fpr, tpr, _ = metrics.roc_curve(y_test,  y_pred_proba)
auc = metrics.roc_auc_score(y_test, y_pred_proba)
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()