def main():
# Load user ratings
raw_training_dataset_df = pd.read_csv(
'movie_ratings_data_set_training.csv')
raw_testing_dataset_df = pd.read_csv('movie_ratings_data_set_testing.csv')
# Convert the running list of user ratings into a matrix
ratings_training_df = pd.pivot_table(raw_training_dataset_df,
index='user_id',
columns='movie_id',
aggfunc=np.max)
ratings_testing_df = pd.pivot_table(raw_testing_dataset_df,
index='user_id',
columns='movie_id',
aggfunc=np.max)
# Apply matrix factorization to find the latent features
U, M = matrix_factorization_utilities.low_rank_matrix_factorization(
ratings_training_df.values, num_features=11, regularization_amount=1.1)
# Find all predicted ratings by multiplying U and M
predicted_ratings = np.matmul(U, M)
# Measure RMSE
rmse_training = matrix_factorization_utilities.RMSE(
ratings_training_df.values, predicted_ratings)
rmse_testing = matrix_factorization_utilities.RMSE(
ratings_testing_df.values, predicted_ratings)
print("Training RMSE: {}".format(rmse_training))
print("Testing RMSE: {}".format(rmse_testing))
def stratLearn(self):
"""
Learn user use other users by matrix fuctorization mathod.
first create pivot table matrix of users, products and purchases.
create two matrix by factorization matrix :
U-users features
P-products features
predicted purchases list get from multiplied U and P matrix
"""
self.setDataFrames()
#normalize quntity
self.user_product_purch_df_normalized = self.normalize_quantity()
purchases = pd.pivot_table(self.user_product_purch_df_normalized,
index='user_num',
columns='product_num',
aggfunc=np.max)
U, P = matrix_factorization_utilities.low_rank_matrix_factorization(
purchases.as_matrix(), num_features=15, regularization_amount=3.6)
predicted_purchases = np.matmul(U, P)
P = np.transpose(P)
pickle.dump(U, open("user_features.dat", "wb"))
pickle.dump(P, open("product_features.dat", "wb"))
pickle.dump(predicted_purchases, open("predicted_purchases.dat", "wb"))
rmse = matrix_factorization_utilities.RMSE(purchases.as_matrix(),
predicted_purchases)
# Load user ratings
raw_training_dataset_df = pd.read_csv(
"data/movie_ratings_data_set_training.csv")
raw_testing_dataset_df = pd.read_csv("data/movie_ratings_data_set_testing.csv")
# Convert the running list of user ratings into a matrix
ratings_training_df = pd.pivot_table(raw_training_dataset_df,
index='user_id',
columns='movie_id',
aggfunc=np.max)
ratings_testing_df = pd.pivot_table(raw_testing_dataset_df,
index='user_id',
columns='movie_id',
aggfunc=np.max)
# Apply matrix factorization to find latent features
U, M = mfu.low_rank_matrix_factorization(ratings_training_df.as_matrix(),
num_features=11,
regularization_amount=1.1)
# Find all predicted ratings by multiplying U and M
predicted_ratings = np.matmul(U, M)
# Measure RMSE
rmse_training = mfu.RMSE(ratings_training_df.as_matrix(), predicted_ratings)
rmse_testing = mfu.RMSE(ratings_testing_df.as_matrix(), predicted_ratings)
print("Training RMSE: {}".format(rmse_training))
print("Testing RMSE: {}".format(rmse_testing))
import numpy as np
import pandas as pd
import matrix_factorization_utilities
# Load user ratings
raw_training_dataset_df = pd.read_csv('movie_ratings_data_set_training.csv')
raw_testing_dataset_df = pd.read_csv('movie_ratings_data_set_testing.csv')
# Convert the running list of user ratings into a matrix
ratings_training_df = pd.pivot_table(raw_training_dataset_df, index='user_id', columns='movie_id', aggfunc=np.max)
ratings_testing_df = pd.pivot_table(raw_testing_dataset_df, index='user_id', columns='movie_id', aggfunc=np.max)
# Apply matrix factorization to find the latent features
U, M = matrix_factorization_utilities.low_rank_matrix_factorization(ratings_training_df.as_matrix(),
num_features=11,
regularization_amount=1.0)
# Find all predicted ratings by multiplying U and M
predicted_ratings = np.matmul(U, M)
# Measure RMSE
rmse_training = matrix_factorization_utilities.RMSE(ratings_training_df.as_matrix(), predicted_ratings)
rmse_testing = matrix_factorization_utilities.RMSE(ratings_testing_df.as_matrix(), predicted_ratings)
print("Training RMSE: {}".format(rmse_training))
print("Testing RMSE: {}".format(rmse_testing))
'movie_ratings_data_set_training.csv')
users_movie_ratings_testing = pandas.read_csv(
'movie_ratings_data_set_testing.csv')
users_movie_ratings_training_pivot_table = pandas.pivot_table(
users_movie_ratings_training,
index='user_id',
columns='movie_id',
aggfunc=numpy.max)
users_movie_ratings_testing_pivot_table = pandas.pivot_table(
users_movie_ratings_testing,
index='user_id',
columns='movie_id',
aggfunc=numpy.max)
U, M = matrix_factorization_utilities.low_rank_matrix_factorization(
users_movie_ratings_training_pivot_table.as_matrix(),
num_features=11,
regularization_amount=1.1)
predicted_ratings = numpy.matmul(U, M)
# Measure RMSE
rmse_training = matrix_factorization_utilities.RMSE(
users_movie_ratings_training_pivot_table.as_matrix(), predicted_ratings)
rmse_testing = matrix_factorization_utilities.RMSE(
users_movie_ratings_testing_pivot_table.as_matrix(), predicted_ratings)
print('Training RMSE: {}'.format(rmse_training))
print('Testing RMSE: {}'.format(rmse_testing))
