class RidgeClassifierCVImpl():
def __init__(self,
alphas=[0.1, 1.0, 10.0],
fit_intercept=True,
normalize=False,
scoring=None,
cv=None,
class_weight='balanced',
store_cv_values=False):
self._hyperparams = {
'alphas': alphas,
'fit_intercept': fit_intercept,
'normalize': normalize,
'scoring': scoring,
'cv': cv,
'class_weight': class_weight,
'store_cv_values': store_cv_values
}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def predict(self, X):
return self._sklearn_model.predict(X)
def test_class_weights_cv():
# Test class weights for cross validated ridge classifier.
X = np.array([[-1.0, -1.0], [-1.0, 0], [-0.8, -1.0], [1.0, 1.0], [1.0, 0.0]])
y = [1, 1, 1, -1, -1]
clf = RidgeClassifierCV(class_weight=None, alphas=[0.01, 0.1, 1])
clf.fit(X, y)
# we give a small weights to class 1
clf = RidgeClassifierCV(class_weight={1: 0.001}, alphas=[0.01, 0.1, 1, 10])
clf.fit(X, y)
assert_array_equal(clf.predict([[-0.2, 2]]), np.array([-1]))
def test_class_weights_cv():
# Test class weights for cross validated ridge classifier.
X = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0], [1.0, 1.0], [1.0,
0.0]])
y = [1, 1, 1, -1, -1]
clf = RidgeClassifierCV(class_weight=None, alphas=[.01, .1, 1])
clf.fit(X, y)
# we give a small weights to class 1
clf = RidgeClassifierCV(class_weight={1: 0.001}, alphas=[.01, .1, 1, 10])
clf.fit(X, y)
assert_array_equal(clf.predict([[-.2, 2]]), np.array([-1]))
def _test_ridge_classifiers(filter_):
n_classes = np.unique(y_iris).shape[0]
n_features = X_iris.shape[1]
for reg in (RidgeClassifier(), RidgeClassifierCV()):
reg.fit(filter_(X_iris), y_iris)
assert_equal(reg.coef_.shape, (n_classes, n_features))
y_pred = reg.predict(filter_(X_iris))
assert_greater(np.mean(y_iris == y_pred), .79)
cv = KFold(5)
reg = RidgeClassifierCV(cv=cv)
reg.fit(filter_(X_iris), y_iris)
y_pred = reg.predict(filter_(X_iris))
assert_true(np.mean(y_iris == y_pred) >= 0.8)
def _test_ridge_classifiers(filter_):
n_classes = np.unique(y_iris).shape[0]
n_features = X_iris.shape[1]
for reg in (RidgeClassifier(), RidgeClassifierCV()):
reg.fit(filter_(X_iris), y_iris)
assert_equal(reg.coef_.shape, (n_classes, n_features))
y_pred = reg.predict(filter_(X_iris))
assert_greater(np.mean(y_iris == y_pred), .79)
cv = KFold(5)
reg = RidgeClassifierCV(cv=cv)
reg.fit(filter_(X_iris), y_iris)
y_pred = reg.predict(filter_(X_iris))
assert_true(np.mean(y_iris == y_pred) >= 0.8)
def _test_ridge_classifiers(filter_):
n_classes = np.unique(y_iris).shape[0]
n_features = X_iris.shape[1]
for clf in (RidgeClassifier(), RidgeClassifierCV()):
clf.fit(filter_(X_iris), y_iris)
assert_equal(clf.coef_.shape, (n_classes, n_features))
y_pred = clf.predict(filter_(X_iris))
assert_greater(np.mean(y_iris == y_pred), .79)
n_samples = X_iris.shape[0]
cv = KFold(n_samples, 5)
clf = RidgeClassifierCV(cv=cv)
clf.fit(filter_(X_iris), y_iris)
y_pred = clf.predict(filter_(X_iris))
assert_true(np.mean(y_iris == y_pred) >= 0.8)
def _test_ridge_classifiers(filter_):
n_classes = np.unique(y_iris).shape[0]
n_features = X_iris.shape[1]
for clf in (RidgeClassifier(), RidgeClassifierCV()):
clf.fit(filter_(X_iris), y_iris)
assert_equal(clf.coef_.shape, (n_classes, n_features))
y_pred = clf.predict(filter_(X_iris))
assert_greater(np.mean(y_iris == y_pred), .79)
n_samples = X_iris.shape[0]
cv = KFold(n_samples, 5)
clf = RidgeClassifierCV(cv=cv)
clf.fit(filter_(X_iris), y_iris)
y_pred = clf.predict(filter_(X_iris))
assert_true(np.mean(y_iris == y_pred) >= 0.8)
def test_ridge_classifier_cv_store_cv_values():
x = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0], [1.0, 1.0], [1.0,
0.0]])
y = np.array([1, 1, 1, -1, -1])
n_samples = x.shape[0]
alphas = [1e-1, 1e0, 1e1]
n_alphas = len(alphas)
r = RidgeClassifierCV(alphas=alphas, cv=None, store_cv_values=True)
# with len(y.shape) == 1
n_targets = 1
r.fit(x, y)
assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)
# with len(y.shape) == 2
y = np.array([[1, 1, 1, -1, -1], [1, -1, 1, -1, 1], [-1, -1, 1, -1,
-1]]).transpose()
n_targets = y.shape[1]
r.fit(x, y)
assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)
def test_ridge_classifier_cv_store_cv_values():
x = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
[1.0, 1.0], [1.0, 0.0]])
y = np.array([1, 1, 1, -1, -1])
n_samples = x.shape[0]
alphas = [1e-1, 1e0, 1e1]
n_alphas = len(alphas)
r = RidgeClassifierCV(alphas=alphas, cv=None, store_cv_values=True)
# with len(y.shape) == 1
n_targets = 1
r.fit(x, y)
assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)
# with len(y.shape) == 2
y = np.array([[1, 1, 1, -1, -1],
[1, -1, 1, -1, 1],
[-1, -1, 1, -1, -1]]).transpose()
n_targets = y.shape[1]
r.fit(x, y)
assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)
def result():
if request.method == 'POST':
path = request.files.get('myFile')
df = pd.read_csv(path, encoding="ISO-8859-1")
filename = request.form['filename']
str1 = request.form['feature']
str2 = request.form['label']
if str1 in list(df) and str2 in list(df):
y = df[str2]
X = df[str1]
else:
return render_template('nameError.html')
x = []
for subject in X:
result = re.sub(r"http\S+", "", subject)
replaced = re.sub(r'[^a-zA-Z0-9 ]+', '', result)
x.append(replaced)
X = pd.Series(x)
X = X.str.lower()
"""
texts = []
for doc in X:
doc = nlp(doc, disable=['parser', 'ner'])
tokens = [tok.lemma_.lower().strip() for tok in doc if tok.lemma_ != '-PRON-']
tokens = [tok for tok in tokens if tok not in stopwords]
tokens = ' '.join(tokens)
texts.append(tokens)
X = pd.Series(texts)
"""
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33)
tfidfvect = TfidfVectorizer(ngram_range=(1, 1))
X_train_tfidf = tfidfvect.fit_transform(X_train)
start = time()
clf1 = LinearSVC()
clf1.fit(X_train_tfidf, y_train)
pred_SVC = clf1.predict(tfidfvect.transform(X_test))
a1 = accuracy_score(y_test, pred_SVC)
end = time()
print("accuracy SVC: {} and time: {} s".format(a1, (end - start)))
start = time()
clf2 = LogisticRegression(n_jobs=-1,
multi_class='multinomial',
solver='newton-cg')
clf2.fit(X_train_tfidf, y_train)
pred_LR = clf2.predict(tfidfvect.transform(X_test))
a2 = accuracy_score(y_test, pred_LR)
end = time()
print("accuracy LR: {} and time: {}".format(a2, (end - start)))
start = time()
clf3 = RandomForestClassifier(n_jobs=-1)
clf3.fit(X_train_tfidf, y_train)
pred = clf3.predict(tfidfvect.transform(X_test))
a3 = accuracy_score(y_test, pred)
end = time()
print("accuracy RFC: {} and time: {}".format(a3, (end - start)))
start = time()
clf4 = MultinomialNB()
clf4.fit(X_train_tfidf, y_train)
pred = clf4.predict(tfidfvect.transform(X_test))
a4 = accuracy_score(y_test, pred)
end = time()
print("accuracy MNB: {} and time: {}".format(a4, (end - start)))
start = time()
clf5 = GaussianNB()
clf5.fit(X_train_tfidf.toarray(), y_train)
pred = clf5.predict(tfidfvect.transform(X_test).toarray())
a5 = accuracy_score(y_test, pred)
end = time()
print("accuracy GNB: {} and time: {}".format(a5, (end - start)))
start = time()
clf6 = LogisticRegressionCV(n_jobs=-1)
clf6.fit(X_train_tfidf, y_train)
pred_LR = clf6.predict(tfidfvect.transform(X_test))
a6 = accuracy_score(y_test, pred_LR)
end = time()
print("accuracy LRCV: {} and time: {}".format(a6, (end - start)))
start = time()
clf7 = AdaBoostClassifier()
clf7.fit(X_train_tfidf, y_train)
pred_LR = clf7.predict(tfidfvect.transform(X_test))
a7 = accuracy_score(y_test, pred_LR)
end = time()
print("accuracy ABC: {} and time: {}".format(a7, (end - start)))
start = time()
clf8 = BernoulliNB()
clf8.fit(X_train_tfidf.toarray(), y_train)
pred = clf8.predict(tfidfvect.transform(X_test).toarray())
a8 = accuracy_score(y_test, pred)
end = time()
print("accuracy BNB: {} and time: {}".format(a8, (end - start)))
start = time()
clf9 = Perceptron(n_jobs=-1)
clf9.fit(X_train_tfidf.toarray(), y_train)
pred = clf9.predict(tfidfvect.transform(X_test).toarray())
a9 = accuracy_score(y_test, pred)
end = time()
print("accuracy Per: {} and time: {}".format(a9, (end - start)))
start = time()
clf10 = RidgeClassifierCV()
clf10.fit(X_train_tfidf.toarray(), y_train)
pred = clf10.predict(tfidfvect.transform(X_test).toarray())
a10 = accuracy_score(y_test, pred)
end = time()
print("accuracy RidCV: {} and time: {}".format(a10, (end - start)))
start = time()
clf11 = SGDClassifier(n_jobs=-1)
clf11.fit(X_train_tfidf.toarray(), y_train)
pred = clf11.predict(tfidfvect.transform(X_test).toarray())
a11 = accuracy_score(y_test, pred)
end = time()
print("accuracy SGDC: {} and time: {}".format(a11, (end - start)))
start = time()
clf12 = SGDClassifier(n_jobs=-1)
clf12.fit(X_train_tfidf.toarray(), y_train)
pred = clf12.predict(tfidfvect.transform(X_test).toarray())
a12 = accuracy_score(y_test, pred)
end = time()
print("accuracy XGBC: {} and time: {}".format(a12, (end - start)))
acu_list = [a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, a11, a12]
max_list = max(acu_list)
if max_list == a1:
pickle.dump(clf1, open(filename + '_model', 'wb'))
elif max_list == a2:
pickle.dump(clf2, open(filename + '_model', 'wb'))
elif max_list == a3:
pickle.dump(clf3, open(filename + '_model', 'wb'))
elif max_list == a4:
pickle.dump(clf4, open(filename + '_model', 'wb'))
elif max_list == a5:
pickle.dump(clf5, open(filename + '_model', 'wb'))
elif max_list == a6:
pickle.dump(clf6, open(filename + '_model', 'wb'))
elif max_list == a7:
pickle.dump(clf7, open(filename + '_model', 'wb'))
elif max_list == a8:
pickle.dump(clf8, open(filename + '_model', 'wb'))
elif max_list == a9:
pickle.dump(clf9, open(filename + '_model', 'wb'))
elif max_list == a10:
pickle.dump(clf10, open(filename + '_model', 'wb'))
elif max_list == a11:
pickle.dump(clf11, open(filename + '_model', 'wb'))
elif max_list == a12:
pickle.dump(clf12, open(filename + '_model', 'wb'))
pickle.dump(tfidfvect, open(filename + '_tfidfVect', 'wb'))
return render_template("result.html",
ac1=a1,
ac2=a2,
ac3=a3,
ac4=a4,
ac5=a5,
ac6=a6,
ac7=a7,
ac8=a8,
ac9=a9,
ac10=a10,
ac11=a11,
ac12=a12)
