Text Classification

text_classification.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer

#Are the tags which we are using currently for tagging the sentences
my_tags = ['Social','Economic','Political','Health','Environmental','Ministry','Aim/Objective/Goal','Rural Development','Scheme','Proposed','Brief','Organization','Remedy','Defence','Foreign Relations','Science & Technology','Location','Facts','Space Science','Cultural','Future','International']

#reading the file which has our data
df = pd.read_csv("out1.csv")

#Using only the data for which we have the tags available and splitting the data into training and testing sets
X = df['Text'][0:65]
y = df['Class'][0:65]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state = 42)


#Making a pipeline where we are first creating the vectors then transforming those and finally applying our classifier
nb = Pipeline([('vect', CountVectorizer()),
               ('tfidf', TfidfTransformer()),
               ('clf', MultinomialNB()),
              ])
nb.fit(X_train, y_train)
y_pred = nb.predict(X_test)

#print('accuracy %s' % accuracy_score(y_pred, y_test))
#print(classification_report(y_test, y_pred,target_names=my_tags))


print(X_test,y_pred,y_test)

Dataset looks like: