from sklearn.datasets import fetch_20newsgroups
text_data= fetch_20newsgroups()
print("Keys : \n{}".format(text_data.keys()))
print(text_data.target_names)
print(text_data.data[1])
categories= ['sci.space','rec.sport.hockey','rec.motorcycles','rec.sport.baseball']
train = fetch_20newsgroups(subset='train',categories= categories)
test = fetch_20newsgroups(subset='test',categories=categories)
print(train.data[5])
print(test.data[5])
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
model = make_pipeline(TfidfVectorizer(), MultinomialNB())
model.fit(train.data,train.target)
labels=model.predict(test.data)
from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
mat = confusion_matrix(test.target, labels)
sns.heatmap(mat.T, square=True, annot=True, fmt='d', cbar=True, cmap="YlGnBu",vmin=3,vmax=8,
            xticklabels=train.target_names, yticklabels=train.target_names)
plt.xlabel('true label')
plt.ylabel('predicted label')
plt.show()