def ML_analysis(X_train, X_test, y_train, y_test, data):
X_train_counts, count_vectorizer = mo.vectorizer(
X_train, (2, 2))
# transforming testing data into document-term matrix
X_test_counts = count_vectorizer.transform(
X_test)
pipeline = Pipeline(
[('clf', LogisticRegression(solver='saga', multi_class='multinomial', class_weight='balanced'))])
parameters = {'clf__penalty': ['l1', 'l2'],
'clf__C': [0.001, .009, 0.01, .09, 1, 2, 5, 10, 25, 30, 40]}
# scorers = {
# 'precision_score': make_scorer(precision_score),
# 'recall_score': make_scorer(recall_score),
# 'accuracy_score': make_scorer(accuracy_score)}
scoring = ['precision_macro', 'recall_macro', 'f1_macro', 'balanced_accuracy']
grid_search = RandomizedSearchCV(pipeline, parameters, cv=5, n_iter=10,
n_jobs=-1, verbose=1, scoring=scoring, refit='recall_macro')
#
grid_search.fit(X_train_counts, y_train)
grid_search.best_score_
best_parameters = grid_search.best_params_
print(best_parameters)
print(grid_search.best_score_)
predicted_level = grid_search.predict(X_test_counts)
print(grid_search.best_estimator_)
print_summary(y_test, predicted_level,
data, "Cat_level")
plot.plot_confusion_matrix(y_test, predicted_level, classes=data.groupby('Cat_level').count().index,
title='Confusion matrix, without normalization')
def ML_analysis(X_train, y_train, data, colum_name):
X_train_counts, count_vectorizer = mo.vectorizer(
X_train, (1, 1))
logreg = LogisticRegression(
) # C=30.0, class_weight='balanced', solver='newton-cg',
# multi_class='multinomial', n_jobs=-1, random_state=40)
#ist_features = X_train_counts
#list_labels = data[colum_name].tolist()
predicted = cross_val_predict(logreg, X_train_counts, y_train, cv=3)
print(metrics.accuracy_score(y_train, predicted))
print(metrics.classification_report(y_train, predicted))
def ML_analysis(X_train, X_test, y_train, y_test, data):
X_train_counts, count_vectorizer = mo.vectorizer(X_train, (1, 2))
X_test_counts = count_vectorizer.transform(X_test)
logreg = LogisticRegression(
C=1) # C=30.0, class_weight='balanced', solver='newton-cg',
# multi_class='multinomial', n_jobs=-1, random_state=40)
predicted_level = mo.train_model(logreg, X_train_counts, y_train,
X_test_counts)
print_summary(y_test, predicted_level, data, "Cat_level")
plot.plot_confusion_matrix(y_test,
predicted_level,
classes=data.groupby('Cat_level').count().index,
title='Confusion matrix, without normalization')
Real_data = pd.read_csv('/Users/ruddirodriguez/Dropbox/Machine_Learning/NLP/' +
real_data_name)
real_data_clean = preparing_data(Real_data)
training_data_clean = preparing_data(training_data)
#real_data_clean = real_data_clean[real_data_clean['Level'] ==5]
#training_data_clean = training_data_clean[(
# training_data_clean['Level'] == 5) | (training_data_clean['Level'] == 2)]
#fig = plt.figure(figsize=(8, 6))
#plot.number_of_levels(real_data_clean)
#
#fig = plt.figure(figsize=(8, 6))
#plot.number_of_levels(training_data_clean)
X_train_counts, count_vectorizer = mo.vectorizer(
training_data_clean['lemmatizing'].tolist(), (1, 1))
# transforming testing data into document-term matrix
X_test_counts = count_vectorizer.transform(
real_data_clean['lemmatizing'].tolist())
y_train = training_data_clean["Level"].tolist()
y_test = real_data_clean["Level"].tolist()
NB = MultinomialNB(alpha=0.5)
predicted_level = mo.train_model(NB, X_train_counts, y_train, X_test_counts)
print_summary(y_test, predicted_level, training_data_clean, "Cat_level")
accuracy, precision, recall, harmonic_mean = mo.get_metrics(
#
#worcloud_generation (text)
## Create and generate a word cloud image:
#wordDict = {
#'data': '',
#'year': '',
#'science':''}
#text_copy = multipleReplace(text, wordDict)
#worcloud_generation (text_copy)
list_data_frames = []
cc = 0
for i in training_data_clean['Cat_level'].value_counts().index:
cc += 1
data = training_data_clean[training_data_clean['Level'] == cc]
X_train_counts, count_vectorizer = mo.vectorizer(
data['lemmatizing'].tolist(), (1, 2))
freqss = pd.DataFrame(
[(word, X_train_counts.getcol(idx).sum(), i)
for word, idx in count_vectorizer.vocabulary_.items()],
columns=['word', 'Freq', 'Level']).sort_values(by='Freq',
ascending=False)
list_data_frames.append(freqss)
text = " ".join(item for item in data['lemmatizing'].tolist())
wordDict = {'data': '', 'year': '', 'science': ''}
savepath = (
"/Users/ruddirodriguez/Dropbox/Machine_Learning/Data_Science_day_UU/" +
i + "." + "svg")
text_copy = multipleReplace(text, wordDict)
worcloud_generation(text_copy, savepath)