def train_model():
training_data = pd.read_pickle("..//data//lemmatized_train_dataframe.pkl")
train_features = []
for feature in training_data[0]:
feature = feature.lower()
train_features.append(feature)
targets = []
targets.append(training_data[1])
targets.append(training_data[2])
targets.append(training_data[3])
targets.append(training_data[4])
targets.append(training_data[5])
targets.append(training_data[6])
logis = LogisticRegressor()
logis = logis.train_model(train_features, targets)
pickle.dump(logis, open("../data/logistic_model.pkl", "wb"))
def predict():
ids, comments = loadQuestionsFromTestDF()
logis = LogisticRegressor()
final_submission = open("final.csv", "w+")
for i, text in enumerate(comments):
print(ids[i])
text = str(text).lower()
text = re.sub(r'[^\w\s]', '', text)
text = remove_stop_words([text.lower()])
text = lemmatize(text[0])
results = logis.predict([text])[0]
line = str(ids[i]) + ","
for res in results:
line += str(round(res, 2)) + ","
line = line[0:len(line) - 1]
print(line)
final_submission.write(line + "\n")
def setUp(self):
self.logreg = LogisticRegressor(self.train_dataset, self.train_labels)
import numpy as np
import random
from logistic_regression import LogisticRegressor
X = np.random.rand(380, 30)
y = [0] * 300 + [1] * 80
random.shuffle(y)
y = np.array(y)
# y = np.reshape(y,(380,1))
# print(y)
print("X:\n", X)
print("y:\n", y)
lr = LogisticRegressor(X, y)
lr.train_model(verbose=True)
# Importing libraries and modules
import pandas as pd
from utils import *
from logistic_regression import LogisticRegressor
# Reading data into variables.
X = pd.read_csv("breast_data.csv", header=None).to_numpy()
y = pd.read_csv("breast_truth.csv", header=None).to_numpy()
# Splitting data into train/test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# Creating model
model = LogisticRegressor(learning_rate=0.0001, n_iterations=100)
model.fit(X_train, y_train)
# Predict test data for evaluate model
predict_test = model.predict(X_test)
print("Accuracy of model on test data: %2.2f" % accuracy(y_test, predict_test))
