Wann-Jiun

Wann-Jiun

Wann-Jiun

df_id = pd.read_csv('links.csv', sep=',')

idx_to_movie = {}
for row in df_id.itertuples():
    idx_to_movie[row[1]-1] = row[2]  
    
total_movies = 9000

movies = [0]*total_movies
for i in range(len(movies)):

Wann-Jiun

import requests
import json

from IPython.display import Image
from IPython.display import display
from IPython.display import HTML

idx_to_movie = {}
for row in df_id.itertuples():
    idx_to_movie[row[1]-1] = row[2]

Wann-Jiun

from sklearn.metrics import mean_squared_error

prediction = similarity_user.dot(train_matrix) / np.array([np.abs(similarity_user).sum(axis=1)]).T
prediction = prediction[test_matrix.nonzero()].flatten()
test_vector = test_matrix[test_matrix.nonzero()].flatten()
mse = mean_squared_error(prediction, test_vector)

print 'MSE = ' + str(mse)

Wann-Jiun

similarity_user = train_matrix.dot(train_matrix.T) + 1e-9
norms = np.array([np.sqrt(np.diagonal(similarity_user))])
similarity_user = ( similarity_user / (norms * norms.T) )

similarity_movie = train_matrix.T.dot(train_matrix) + 1e-9
norms = np.array([np.sqrt(np.diagonal(similarity_movie))])
similarity_movie = ( similarity_movie / (norms * norms.T) )

Wann-Jiun

train_matrix = rating_matrix.copy()
test_matrix = np.zeros(ratings_matrix.shape)

for i in xrange(rating_matrix.shape[0]):
    rating_idx = np.random.choice(
        rating_matrix[i, :].nonzero()[0], 
        size=10, 
        replace=True)
    train_matrix[i, rating_idx] = 0.0
    test_matrix[i, rating_idx] = rating_matrix[i, rating_idx]

Wann-Jiun

sparsity = float(len(ratings.nonzero()[0]))
sparsity /= (ratings.shape[0] * ratings.shape[1])
sparsity *= 100

Wann-Jiun

df = pd.read_csv('ratings.csv', sep=',')
df_id = pd.read_csv('links.csv', sep=',')
df = pd.merge(df, df_id, on=['movieId'])

rating_matrix = np.zeros((df.userId.unique().shape[0], max(df.movieId)))
for row in df.itertuples():
    rating_matrix[row[1]-1, row[2]-1] = row[3]
rating_matrix = rating_matrix[:,:9000]

Wann-Jiun

# Extra Trees Regressor

et_regr = ExtraTreesRegressor()
et_regr.fit(train_df_munged, label_df)

# Run prediction on training set to get a rough idea of how well it does.
y_pred = et_regr.predict(train_df_munged)
y_test = label_df
print("Extra Trees Regressor score on training set: ", rmse(y_test, y_pred))