def binary_naive_bayes():
model = nb.NaiveBayesModel()
clean = cn.DataCLean()
doc_vector = dv.DocumentVector()
df_clean, uniqueWords = clean.Clean()
df_clean_test, df_clean_train = split(
df_clean, 0, int(.3 * (df_clean['class'].count())))
docVector = doc_vector.binary_docvector(df_clean_train, uniqueWords)
# print(docVector)
df_WordGivenPI, df_WordGivenNoPi, Prob_PI, Prob_NoPI, numWordsInPI, numWordsInNoPI = model.TrainModel(
docVector, uniqueWords)
# print("Model Trained")
predict_df, test_data = model.predict(Prob_PI, Prob_NoPI, uniqueWords,
df_WordGivenPI, df_WordGivenNoPi,
numWordsInPI, numWordsInNoPI,
df_clean_test, clean)
print(
"--------------Binary Naive Bayes Accuracy Stats---------------------------"
)
stats = em.Evaluate()
TP, FN, TN, FP = stats.confusion_matrix(test_data, predict_df)
print("Accuracy = ", stats.Accuracy(TP, TN, FP, FN))
print("Precision = ", stats.Precision(TP, FP))
print("Recall = ", stats.Recall(TP, FN))
print("fScore = ", stats.fScore(TP, FN, FP))
print("True Negative = ", stats.TrueNegative(TN, FP))
print(
"---------------------------------------------------------------------"
)
def binary_naive_bayes_kfold():
model = nb.NaiveBayesModel()
clean = cn.DataCLean()
doc_vector = dv.DocumentVector()
final_df, df = clean.extract(pathData)
count = 0
start = -200
end = 0
accuracy = []
precision = []
recall = []
fscore = []
true_neg = []
stats = em.Evaluate()
for count in range(5):
start = start + 200
end = end + 200
df_test, df_train = split(final_df, start, end)
# print(df_train)
li_clean_text, df_clean = clean.clean_data(df_train)
uniqueWords = clean.make_unique_li(li_clean_text)
# # print(uniqueWords)
docVector = doc_vector.binary_docvector(df_clean, uniqueWords)
df_WordGivenPI, df_WordGivenNoPi, Prob_PI, Prob_NoPI, numWordsInPI, numWordsInNoPI = model.TrainModel(
docVector, uniqueWords)
predict_df, punc_df = model.predict(Prob_PI, Prob_NoPI, uniqueWords,
df_WordGivenPI, df_WordGivenNoPi,
numWordsInPI, numWordsInNoPI,
df_test, clean)
# print("--------------Naive Bayes Accuracy Stats---------------------------")
TP, FN, TN, FP = stats.confusion_matrix(punc_df, predict_df)
accuracy.append(stats.Accuracy(TP, TN, FP, FN))
precision.append(stats.Precision(TP, FP))
recall.append(stats.Recall(TP, FN))
fscore.append(stats.fScore(TP, FN, FP))
true_neg.append(stats.TrueNegative(TN, FP))
# print("---------------------------------------------------------------------")
print(
"---------------------------------------------------------------------"
)
print("Binary Naive Bayes wit k-fold Accuracy Stats")
print("accuracy = ", accuracy)
print("precison = ", precision)
print("recall = ", recall)
print("f-score = ", fscore)
print("True Negative = ", true_neg)
print("accuracy = ", Average(accuracy))
print("precison = ", Average(precision))
print("recall = ", Average(recall))
print("f-score = ", Average(fscore))
print("true negative = ", Average(true_neg))
def generatingTrainSet():
_dcl = cl.DataCLean()
final_df, uniqueWords = _dcl.Clean()
_dv = dv.DocumentVector()
# docVector = _dv.tf_idf(final_df, uniqueWords)
docVector = _dv.DocVector(final_df, uniqueWords)
# docVector = _dv.binary_docvector(final_df, uniqueWords)
# -------------------------------------------------------------------------
# using textblob dict approach
# import NaiveBayesTextBlob as tb
# polarity_docVector = tb.text_blob(docVector, uniqueWords)
# docVector = polarity_docVector
# -------------------------------------------------------------------------
df = docVector.values
X_train, Y = df[:, :-1], df[:, -1]
Y_train = convert_to_0_or_1(Y)
return (X_train, Y_train)
