test_labels = []
for row in test_corpus:
test_data.append(row[0])
test_labels.append(row[1])
# Create feature vectors
vectorizer = TfidfVectorizer(min_df = 4, max_df = 0.9)
# Train the feature vectors
train_vectors = vectorizer.fit_transform(train_data)
# Apply model on test data
test_vectors = vectorizer.transform(test_data)
# Perform classification with SVM, kernal = linear
model = svm.SVC(kernel = 'linear')
model.fit(train_vectors, train_labels)
prediction = model.predict(test_vectors)
print(classification_report(test_labels, prediction))
# Text Matching / Similarity
# Levenshtein Distance
def levenshtein(s1, s2):
if len(s1) > len(s2):
s1, s2 = s2, s1
distances = range(len(s1) + 1)
for index2, char2 in enumerate(s2):
newDistances = [index2 + 1]
for index1, char1 in enumerate(s1):
if char1 == char2:
newDistances.append(distances[index1])
# Random Forest:
# Instead of doing these steps one at a time, we can use a pipeline to complete them all at once
randomforest = Pipeline([('vect', vectorizer),
('chi', SelectKBest(chi2, k=1200)),
('clf', RandomForestClassifier(random_state=42))])
# fitting our model and save it in a pickle for later use
model = randomforest.fit(X_train, y_train)
with open('RandomForest.pickle', 'wb') as f:
pickle.dump(model, f)
ytest = np.array(y_test)
# Evaluating Results:
# Confusion Matrix:
con_mat = cm(ytest, model.predict(X_test))
confusion_matrix = ConfusionMatrix(ytest, model.predict(X_test))
print("Confusion matrix for Random Forest:\n%s" % confusion_matrix)
print(
'For Random Forest model: \nPrecision: {0:.3f} \nRecall: {1:.3f} \nf1score: {2:.3f} \nAccuracy: {3:.3f}'
.format(precision_average(con_mat), recall_average(con_mat),
f1score(con_mat), accuracy(con_mat)))
# Confusion matrix plot:
acc = accuracy(con_mat)
confusion_matrix.plot(normalized=True)
plt.title('Random Forest \nAccuracy:{0:.3f}'.format(acc))
plt.show()
