def main():
reviews = load()
err = []
for i in range(reviews.shape[0]):
err.append(
train_test(reviews[i], np.delete(reviews, i, 0))
)
revs = (reviews > 0).sum(1)
err = np.array(err)
rmse = np.sqrt(err / revs[:, None])
rmse_model, rmse_null = np.mean(rmse, 0)
print("Average of RMSE / Null-model RMSE")
print("{:.2}\t{:.2} (improvement: {:.1%}".format(rmse_model, rmse_null, (rmse_null-rmse_model)/rmse_null))
print()
rmse_model, rmse_null = np.mean(rmse[revs > 60], 0)
print("Average of RMSE / Null-model RMSE (users with more than 60 reviewed movies)")
print("{:.2}\t{:.2} (improvement: {:.1%}".format(rmse_model, rmse_null, (rmse_null-rmse_model)/rmse_null))
# This code is supporting material for the book
# Building Machine Learning Systems with Python
# by Willi Richert and Luis Pedro Coelho
# published by PACKT Publishing
#
# It is made available under the MIT License
from load_ml100k import load
from matplotlib import pyplot as plt
data = load()
data = data.toarray()
plt.gray()
plt.imshow(data[:200, :200], interpolation='nearest')
plt.xlabel('User ID')
plt.ylabel('Film ID')
plt.savefig('../1400_08_03+.png')
from __future__ import print_function
from all_correlations import all_correlations
import numpy as np
from scipy import sparse
from load_ml100k import load
reviews = load()
def estimate_user(user, rest):
bu = user > 0
br = rest > 0
ws = all_correlations(bu,br)
selected = ws.argsort()[-100:]
estimates = rest[selected].mean(0)
estimates /= (.1+br[selected].mean(0))
return estimates
def train_test(user, rest):
estimates = estimate_user(user, rest)
bu = user > 0
br = rest > 0
err = estimates[bu]-user[bu]
null = rest.mean(0)
null /= (.1+br.mean(0))
nerr = null[bu]-user[bu]
return np.dot(err,err), np.dot(nerr, nerr)
def cross_validate_all():
err = []
for i in xrange(reviews.shape[0]):
err.append(
train_test(reviews[i], np.delete(reviews, i, 0))
if reviews[uid, ell] > 0:
pred = reviews[uid, ell]
if c == k:
return pred
c += 1
return pred
def all_estimates(reviews, k=1):
reviews = reviews.astype(float)
k -= 1
nusers, nmovies = reviews.shape
estimates = np.zeros_like(reviews)
for u in range(nusers):
ureviews = np.delete(reviews, u, 0)
ureviews -= ureviews.mean(0)
ureviews /= (ureviews.std(0) + 1e-4)
ureviews = ureviews.T.copy()
for m in np.where(reviews[u] > 0)[0]:
estimates[u, m] = nn_movie(ureviews, reviews, u, m, k)
return estimates
if __name__ == '__main__':
reviews = load().toarray()
estimates = all_estimates(reviews)
error = (estimates - reviews)
error **= 2
error = error[reviews > 0]
print(np.sqrt(error).mean())
def __init__(self):
if AbstractEstimateBase.reviews is None:
AbstractEstimateBase.reviews = load()
if ell == mid:
continue
if reviews[uid,ell] > 0:
pred = reviews[uid,ell]
if c == k:
return pred
c += 1
return pred
def all_estimates(reviews, k=1):
reviews = reviews.astype(float)
k -= 1
nusers, nmovies = reviews.shape
estimates = np.zeros_like(reviews)
for u in range(nusers):
ureviews = np.delete(reviews, u, 0)
ureviews -= ureviews.mean(0)
ureviews /= (ureviews.std(0)+1e-4)
ureviews = ureviews.T.copy()
for m in np.where(reviews[u] > 0)[0]:
estimates[u,m] = nn_movie(ureviews, reviews, u, m, k)
return estimates
if __name__ == '__main__':
reviews = load().toarray()
estimates = all_estimates(reviews)
error = (estimates-reviews)
error **= 2
error = error[reviews > 0]
print(np.sqrt(error).mean())
def __init__(self):
if AbstractEstimateBase.reviews is None:
AbstractEstimateBase.reviews = load()
