Answers for "how to plot confusion matrix in python"

sklearn plot confusion matrix

import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix, plot_confusion_matrix

clf = # define your classifier (Decision Tree, Random Forest etc.)
clf.fit(X, y) # fit your classifier

# make predictions with your classifier
y_pred = clf.predict(X) 
        
# optional: get true negative (tn), false positive (fp)
# false negative (fn) and true positive (tp) from confusion matrix
M = confusion_matrix(y, y_pred)
tn, fp, fn, tp = M.ravel() 

# plotting the confusion matrix
plot_confusion_matrix(clf, X, y)
plt.show()

confusion matrix python

By definition, entry i,j in a confusion matrix is the number of 
observations actually in group i, but predicted to be in group j. 
Scikit-Learn provides a confusion_matrix function:

from sklearn.metrics import confusion_matrix
y_actu = [2, 0, 2, 2, 0, 1, 1, 2, 2, 0, 1, 2]
y_pred = [0, 0, 2, 1, 0, 2, 1, 0, 2, 0, 2, 2]
confusion_matrix(y_actu, y_pred)
# Output
# array([[3, 0, 0],
#        [0, 1, 2],
#        [2, 1, 3]], dtype=int64)

import sklearn.metrics from plot_confusion_matrix

from sklearn.metrics import plot_confusion_matrix

confusion matrix python code

from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_predicted)
cm
# after creating the confusion matrix, for better understaning plot the cm.
import seaborn as sn
plt.figure(figsize = (10,7))
sn.heatmap(cm, annot=True)
plt.xlabel('Predicted')
plt.ylabel('Truth')

how to find the labels of the confusion matrix in python

""" In order to find the labels just use the Counter function to count 
the records from y_test and then check row-wise sum of the confusion 
matrix. Then apply the labels to the corresponding rows using the 
inbuilt seaborn plot as shown below"""

from collections import Counter
Counter(y_test).keys()
Counter(y_test).values()

import seaborn as sns
import matplotlib.pyplot as plt     

ax= plt.subplot()
sns.heatmap(cm, annot=True, fmt='g', ax=ax);  #annot=True to annotate cells, ftm='g' to disable scientific notation

# labels, title and ticks
ax.set_xlabel('Predicted labels');ax.set_ylabel('True labels'); 
ax.set_title('Confusion Matrix'); 
ax.xaxis.set_ticklabels(['business', 'health']); ax.yaxis.set_ticklabels(['health', 'business']);

confusion matrix python

df_confusion = pd.crosstab(y_actu, y_pred, rownames=['Actual'], colnames=['Predicted'], margins=True)