更新文档数据

src/python/16.RecommenderSystems/sklearn-RS-demo-cf.py

@@ -0,0 +1,68 @@
+#!/usr/bin/python
+# coding:utf8
+
+from math import sqrt
+
+import numpy as np
+import pandas as pd
+from scipy.sparse.linalg import svds
+from sklearn import cross_validation as cv
+from sklearn.metrics import mean_squared_error
+from sklearn.metrics.pairwise import pairwise_distances
+
+# 加载数据集
+header = ['user_id', 'item_id', 'rating', 'timestamp']
+# http://files.grouplens.org/datasets/movielens/ml-100k.zip
+dataFile = 'input/16.RecommenderSystems/ml-100k/u.data'
+df = pd.read_csv(dataFile, sep='\t', names=header)
+
+n_users = df.user_id.unique().shape[0]
+n_items = df.item_id.unique().shape[0]
+print 'Number of users = ' + str(n_users) + ' | Number of movies = ' + str(n_items)
+
+# 拆分数据集
+train_data, test_data = cv.train_test_split(df, test_size=0.25)
+
+# 创建用户产品矩阵，针对测试数据和训练数据，创建两个矩阵：
+train_data_matrix = np.zeros((n_users, n_items))
+for line in train_data.itertuples():
+    train_data_matrix[line[1]-1, line[2]-1] = line[3]
+test_data_matrix = np.zeros((n_users, n_items))
+for line in test_data.itertuples():
+    test_data_matrix[line[1]-1, line[2]-1] = line[3]
+# 使用sklearn的pairwise_distances函数来计算余弦相似性。
+user_similarity = pairwise_distances(train_data_matrix, metric="cosine")
+item_similarity = pairwise_distances(train_data_matrix.T, metric="cosine")
+
+
+def predict(rating, similarity, type='user'):
+    if type == 'user':
+        mean_user_rating = rating.mean(axis=1)
+        rating_diff = (rating - mean_user_rating[:, np.newaxis])
+        pred = mean_user_rating[:, np.newaxis] + similarity.dot(rating_diff)/np.array([np.abs(similarity).sum(axis=1)]).T
+    elif type == 'item':
+        pred = rating.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])
+    return pred
+
+
+user_prediction = predict(train_data_matrix, user_similarity, type='user')
+item_prediction = predict(train_data_matrix, item_similarity, type='item')
+
+
+def rmse(prediction, ground_truth):
+    prediction = prediction[ground_truth.nonzero()].flatten()
+    ground_truth = ground_truth[ground_truth.nonzero()].flatten()
+    return sqrt(mean_squared_error(prediction, ground_truth))
+
+
+print 'User based CF RMSE: ' + str(rmse(user_prediction, test_data_matrix))
+print 'Item based CF RMSe: ' + str(rmse(item_prediction, test_data_matrix))
+
+sparsity = round(1.0 - len(df)/float(n_users*n_items), 3)
+print 'The sparsity level of MovieLen100K is ' + str(sparsity * 100) + '%'
+
+
+u, s, vt = svds(train_data_matrix, k=20)
+s_diag_matrix = np.diag(s)
+x_pred = np.dot(np.dot(u, s_diag_matrix), vt)
+print 'User-based CF MSE: ' + str(rmse(x_pred, test_data_matrix))

src/python/16.RecommenderSystems/sklearn-RS-demo-item.py

@@ -0,0 +1,30 @@
+#!/usr/bin/python
+# coding:utf8
+
+import numpy as np
+from sklearn.decomposition import NMF
+import matplotlib.pyplot as plt
+
+RATE_MATRIX = np.array(
+    [[5, 5, 3, 0, 5, 5],
+     [5, 0, 4, 0, 4, 4],
+     [0, 3, 0, 5, 4, 5],
+     [5, 4, 3, 3, 5, 5]]
+)
+
+nmf = NMF(n_components=2)
+user_distribution = nmf.fit_transform(RATE_MATRIX)
+item_distribution = nmf.components_
+
+item_distribution = item_distribution.T
+plt.plot(item_distribution[:, 0], item_distribution[:, 1], "b*")
+plt.xlim((-1, 3))
+plt.ylim((-1, 3))
+
+plt.title(u'the distribution of items (NMF)')
+count = 1
+for item in item_distribution:
+    plt.text(item[0], item[1], 'item '+str(count), bbox=dict(facecolor='red', alpha=0.2),)
+    count += 1
+
+plt.show()

src/python/16.RecommenderSystems/sklearn-RS-demo-user.py

@@ -0,0 +1,31 @@
+#!/usr/bin/python
+# coding:utf8
+
+import numpy as np
+from sklearn.decomposition import NMF
+import matplotlib.pyplot as plt
+
+RATE_MATRIX = np.array(
+    [[5, 5, 3, 0, 5, 5],
+     [5, 0, 4, 0, 4, 4],
+     [0, 3, 0, 5, 4, 5],
+     [5, 4, 3, 3, 5, 5]]
+)
+
+nmf = NMF(n_components=2)
+user_distribution = nmf.fit_transform(RATE_MATRIX)
+item_distribution = nmf.components_
+
+users = ['Ben', 'Tom', 'John', 'Fred']
+zip_data = zip(users, user_distribution)
+
+plt.title(u'the distribution of users (NMF)')
+plt.xlim((-1, 3))
+plt.ylim((-1, 4))
+for item in zip_data:
+    user_name = item[0]
+    data = item[1]
+    plt.plot(data[0], data[1], "b*")
+    plt.text(data[0], data[1], user_name, bbox=dict(facecolor='red', alpha=0.2),)
+
+plt.show()

src/python/16.RecommenderSystems/sklearn-RS-demo.py

@@ -0,0 +1,22 @@
+#!/usr/bin/python
+# coding:utf8
+
+import numpy as np
+from sklearn.decomposition import NMF
+import matplotlib.pyplot as plt
+
+RATE_MATRIX = np.array(
+    [[5, 5, 3, 0, 5, 5],
+     [5, 0, 4, 0, 4, 4],
+     [0, 3, 0, 5, 4, 5],
+     [5, 4, 3, 3, 5, 5]]
+)
+
+nmf = NMF(n_components=2)  # 设有2个隐主题
+user_distribution = nmf.fit_transform(RATE_MATRIX)
+item_distribution = nmf.components_
+
+print '用户的主题分布：'
+print user_distribution
+print '物品的主题分布：'
+print item_distribution