def update_model(db_path, model, batch_size=10000):
conn = sqlite3.connect(db_path)
c = conn.cursor()
c.execute("SELECT * from review_db")
results = c.fetchmany(batch_size)
while results:
data = np.array(results)
X = data[:, 0]
y = data[:, 1].astype(int)
classes = np.array([0, 1])
X_train = vect.transform(X)
model.partial_fit(X_train, y, classes=classes)
results = c.fetchmany(batch_size)
conn.close()
return model
def train(document, y): X = vect.transform([document]) clf.partial_fit(X, [y])
def classify(document):
label = {0: "negative", 1: "positive"}
X = vect.transform([document])
y = clf.predict(X)[0]
proba = np.max(clf.predict_proba(X))
return label[y], proba
import pickle
import re
import os
from vecto import vect
import numpy as np
clf = pickle.load(open("classifier.pkl", "rb"))
label = {0: "negative", 1: "positive"}
example = ["I love this movie"]
X = vect.transform(example)
print("Prediction: %s\nProbability: %.2f%%" %
(label[clf.predict(X)[0]], np.max(clf.predict_proba(X)) * 100))