clf.fit(X_train, y_train)
elif alg == 'nb':
#need original categorical for naive bayes
y_train, y_test = y[train_index], y[test_index]
clf = GaussianNB()
clf.fit(X_train, y_train)
else:
print("unkown classifier " + alg)
y_pred = clf.predict(X_test)
if alg != 'nb':
y_pred = unencode(y_pred)
scores.append(Score(y_test, y_pred))
avg_score = average_scores(scores)
file.write(ds + "," + alg + "," + proc + "," +
str(avg_score.accuracy) + ", " +
str(avg_score.f1_positive) + "," +
str(avg_score.precision_positive) + "," +
str(avg_score.recall_positive) + "," +
str(avg_score.f1_neutral) + "," +
str(avg_score.precision_neutral) + "," +
str(avg_score.recall_neutral) + "," +
str(avg_score.f1_negative) + "," +
str(avg_score.precision_negative) + "," +
str(avg_score.recall_negative) + "\n")
print("accuracy")
print(avg_score.accuracy)
file.close()
"""
from sklearn.naive_bayes import MultinomialNB
from get_data import get_data_tfidf, get_data_custom
from Score import Score, average_scores
from sklearn.model_selection import KFold
X, y = get_data_custom("data-2_train.csv", 3, 2)
kf = KFold(n_splits=10)
kf.get_n_splits(X)
test_scores = []
train_scores = []
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
gnb = MultinomialNB()
gnb.fit(X_train, y_train)
y_pred = gnb.predict(X_test)
test_scores.append(Score(y_test, y_pred))
y_pred = gnb.predict(X_train)
train_scores.append(Score(y_train, y_pred))
average_score = average_scores(test_scores)
print("Average test score: " + str(average_score.accuracy))
average_train_score = average_scores(train_scores)
print("Average train score: " + str(average_train_score.accuracy))
from get_data import get_data_custom, one_hot_encode
from sklearn import tree
from sklearn.model_selection import KFold
from Score import Score, average_scores
print("Decision Tree:\n")
#you can replace this with whatver data getting method you want to try:
#file name, max gram length, min occurances of gram
X, y = get_data_custom('data-1_train.csv', 1, 1)
kf = KFold(n_splits=10)
kf.get_n_splits(X)
test_scores = []
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
dec_tree = tree.DecisionTreeClassifier()
dec_tree.fit(X_train, y_train)
y_pred = dec_tree.predict(X_test)
test_scores.append(Score(y_test, y_pred))
average_score = average_scores(test_scores)
for score in test_scores:
print(score.accuracy)
print("average accuracy: " + str(average_score.accuracy))