def findthemes(nothemes,wordlist,questionresponses,inc_articles,outputfile):
#print questionresponses
synonym_wordlists = []
synonym_wordlist = wordlist
synonym_wordlists = synonym_wordlist.splitlines()
exclude_wordlist = []
stop_path = "englishstop.txt"
stop_words = surveythemer.loadStopWords(stop_path)
surveyQuestionResponse = []
surveyQuestionResponseNID = []
for response in questionresponses:
newresp = remove_html_tags(response["text"])
surveyQuestionResponse.append(newresp)
surveyQuestionResponseNID.append(response["id"])
listOfAllWords, listOfSurveyQuestionWords, listOfAllSurveyQuestionTitles, stemdictionary = surveythemer.getItemWords(surveyQuestionResponse,stop_words)
wordMatrix, listOfWordsIncluded, wordCount, fc, ic = surveythemer.createWordMatrix(listOfAllWords,listOfSurveyQuestionWords)
pc = nothemes
#size of input matrix
ic=shape(wordMatrix)[0]
fc=shape(wordMatrix)[1]
# Random initialization
w=array([[random.random() for j in range(pc)] for i in range(ic)])
h=array([[random.random() for i in range(fc)] for i in range(pc)])
nmfresult = ""
themes = ""
weights,themes = nmf.nmf(wordMatrix,w,h,0.001, 10, 500)
themexml = surveythemer.display_themes(weights,themes,listOfWordsIncluded,surveyQuestionResponse, stemdictionary, wordCount, inc_articles, surveyQuestionResponseNID)
f = open(outputfile, 'w')
f.write(themexml)
f.close()
return
def consensus(V, rank, nloop, method):
"""
Calculate consensus matrix for columns of V
Matrix V has the size of n rows and m columns
n = shape[0]
m = shape[1]
"""
shape = V.shape
m = shape[1]
consensus = np.zeros((m, m))
conn = np.zeros((m, m))
connac = np.zeros((m, m))
for l in range(nloop):
if method == "pnmf":
(W, H) = pnmf.projnmf(V, rank, 0.001, 50, 100)
elif method == "nmf":
(W, H) = nmf.nmf(V, rank, 0.001, 50, 100)
elif method == "spnmf":
(W, H) = spnmf.spnmf(V, rank, 0.001, 50, 100)
elif method == "snmf":
(W, H) = snmf.snmf(V, rank, 0.001, 50, 100)
conn = connectivity(H)
connac = connac + conn
consensus = connac / float(nloop)
return consensus
def multi_evaluation(method, filename, view_names, weights, norm = 'l2', seed="random", post = "direct", data_size=-1):
"""
Eval of baselines (k-means, nmf, svd) on the combined view of all views for multi-view clustering.
:param: method (type: string). Supported methods include "k-means", "nmf", "svd"
:param: filename (type: string). The path of the input multi-view data (.MAT format).
:param: view_names (type: list<string>). View names of the input multi-view data.
:param: weights (type: list<int>). The weight of each view to build the combined view.
:param: norm (type: string). Normalization strategy on the input data. Supported norm methods include:
'l2': each item vector is normalized by its Euclidean length (i.e. l2 distance).
'l1': each item vector is normalized by its sum of all elements (i.e. l1 distance).
'l0': the whole matrix is normalized by the sum of all elements (i.e. l1 normalization on the whole matrix).
:param seed (type: string). The initialization method in CoNMF. Values can be 'k-means' and 'random':
'k-means': initialize W and H matrix using k-means results. The details are seen in paper [1] Section 4.5
'random': randomly initialize W and H matrix.
:param post (type: string). Post processing on W matrix (m*k) to generate clustering result. Values can be 'direct' and 'k-means':
'direct': for each item vector (m*1), use the element with largest value as its cluster assignment.
'k-means': perform k-means on W matrix to get cluster assignment.
:param data_size (type: int). Select the first data_size items to run clustering algorithm.
When the value is -1, the clustering algorithm is run on all items.
This parameter is for a quick check of clustering algorithms in case the input data is too large.
"""
method = method.lower()
if method not in ["k-means","kmeans","nmf","svd"]:
print "Error! Wrong input method name."
return None
# weights can only be integers
if len(view_names)!= len(weights):
print "Error! Length of view_names is not equal to the length of weights!"
return None
datas, names, groundtruth, cluster_k = dl.loadMATdata(filename, view_names,data_size)
data = dl.combineData(datas, weights, norm)
NMIs,As,F1s = [],[],[]
print "Running multi- %s(k=%d,norm=%s,seed=%s,post=%s) for %s, size = %s, #runs: %d" %(method,cluster_k,norm,seed,post,names,str(data.shape), n_runs)
print "view_names = %s, weights = %s" %(str(names),str(weights))
i_run = 1
t0 = time()
while i_run <= n_runs:
t1 = time()
if method == "kmeans" or method=="k-means":
labels = kmeans(data, cluster_k, norm)[0]
if method == "nmf":
labels = nmf(data, cluster_k, norm, seed, post, groundtruth)[0]
if method == "svd":
labels = svd(data, cluster_k, norm, post)
NMI,A,F1,P,RI,ARI = evaluation_scores(groundtruth,labels)
print "\t %d-th run(time=%ds),<Acc, F1, NMI>\t%f\t%f\t%f" %(i_run,time()-t1,A,F1,NMI)
NMIs.append(NMI)
As.append(A)
F1s.append(F1)
i_run = i_run+1
print "Results of %d runs (mean,std_var):\n\t Acc: %f, %f\n\t F1 : %f, %f\n\t NMI: %f, %f" %(n_runs,
np.mean(As),np.std(As),np.mean(F1s),np.std(F1s),np.mean(NMIs),np.std(NMIs))
print "Running time: %fs" %(time() - t0)
def plot_run(plotter):
a = nmf.tf_idf(nmf.read_term_document())
terms = nmf.read_terms()
abort_error = -500
max_iter = 500
num_terms = 3
errors = []
for c in range(2, 7):
term_indices, iterations, best_w, e = nmf.nmf(a, abort_error, max_iter, c, num_terms)
errors.append(e)
plotter(errors)
def train():
"""Train with the train set
Train with the train set, and return the user_user_similarities array.
Returns:
user_user_similarities(Type: numpy.ndarray): The similarities between user and user(user_user_similarities[i, j] represents the similarity between user "i" and user "j". Similarity of oneself is "1".)
user_ids(Type: numpy.ndarray(vector)): user's ids(from small to large) associated with the array
"""
# get user-news array
user_news_array_of_train = numpy.load("user_news_array_of_train.npy")
user_ids_of_train = numpy.load("user_ids_of_train.npy")
user_news_array = user_news_array_of_train
user_ids = user_ids_of_train
user_num = len(user_ids)
del user_news_array_of_train, user_ids_of_train
# NMF
V = numpy.float16(user_news_array.T)
K = 15 # TODO refine this parameter
W, H = nmf.nmf(V, K)
del V, W
# estimatedV = numpy.dot(W, H)
# calculate similarity between users
print("Calculate similarity between users started.")
time_start = time.time()
user_user_similarities = numpy.zeros((user_num, user_num), numpy.float16)
H_norm = numpy.power(H, 2)
H_norm = H_norm.sum(0)
H_norm = numpy.sqrt(H_norm) # norm of each column vector in H
H_norm = numpy.tile(H_norm, (K, 1))
eps = numpy.finfo(float).eps
H_normalized = H / (H_norm + eps)
H_normalized_transpose = H_normalized.transpose()
computed_count = 0
compute_step = 1000 # to avoid MemoryError, only compute a part each time
while computed_count < user_num:
compute_upper_limit = min((computed_count + compute_step, user_num))
user_user_similarities[computed_count:compute_upper_limit, :] = numpy.dot(H_normalized_transpose[computed_count:compute_upper_limit, :], H_normalized)
computed_count += compute_step
del H, H_norm, H_normalized, H_normalized_transpose, computed_count, compute_step
time_end = time.time()
print("Calculate similarity between users ended. %f s cost." % (time_end - time_start))
print("[NMF-User-based Collaborative Filtering] Train finished!")
return user_user_similarities, user_ids
def findthemes(nothemes,wordlist,question_responses,stop_words):
synonym_wordlists = []
synonym_wordlist = wordlist
synonym_wordlists = synonym_wordlist.splitlines()
exclude_wordlist = []
surveyQuestionResponse = []
favourites = []
questionIDs = []
for response in question_responses:
newresp = remove_html_tags(response[0])
for synliststring in synonym_wordlists:
synlist = synliststring.split(",")
mainsyn = synlist[0]
for synword in synlist[1:len(synlist)]:
newresp = newresp.replace(synword,mainsyn)
#print newresp
surveyQuestionResponse.append(newresp)
favourites.append(response[1])
questionIDs.append(response[2])
listOfAllWords, listOfSurveyQuestionWords, listOfAllSurveyQuestionTitles, stemdictionary = surveythemer.getItemWords(surveyQuestionResponse,stop_words)
wordMatrix, listOfWordsIncluded, wordCount, fc, ic = surveythemer.createWordMatrix(listOfAllWords,listOfSurveyQuestionWords)
if (wordMatrix.shape[0] < nothemes+1):
return '{"themesData": "Not enough data"}'
#sys.exit("Not enough data")
w,h = surveythemer.nndsvd(wordMatrix,nothemes,1)
if not h.any():
return '{"themesData": "Empty"}'
# sys.exit("Error message")
nmfresult = ""
themes = ""
weights,themes = nmf.nmf(wordMatrix,w,h,0.001, 10, 500)
json,data = surveythemer.display_themes(weights,themes,listOfWordsIncluded,surveyQuestionResponse, stemdictionary, wordCount, favourites, questionIDs)
# print theme_html
returnData = '{"themesData":'+ data +', "jsonData":'+ json + '}'
return returnData
end_time = time.time()
print('reading test data process finish time: %f' % (end_time - start_time))
training_set_normalize = preprocessing.normalize(training_set, axis=0)
test_set_normalize = preprocessing.normalize(test_set, axis=0)
#===============================
#nmf and knn
#===============================
print('-×-×-×-NMF process begin-×-×-×-')
start_time = time.time()
### NMF
training_W, training_H = nmf(training_set_normalize, n_components, max_iter)
end_time = time.time()
print('NMF process end, time: %f' % (end_time - start_time))
test_H = nmf_keepW(test_set_normalize, training_W)
training_H_trans = training_H.transpose()
test_H_trans = test_H.transpose()
knn(num_neighbors, training_H_trans, training_categorie, test_H_trans,
test_categorie)
#===============================
#new method
#===============================
def getMainFeature(feature, data):
"""
对df_train(test).csv进行特征提取
"""
Log('...get main feature...')
df = copy.deepcopy(data)
# 诊断结果病种提取
case = df['出院诊断病种名称'].replace(np.nan, u' ').values
df['case_length'] = [len(value) for value in case]
df['心脏病'] = [[0, 10]['心脏病' in value] for value in case]
df['肺心病'] = [[0, 4]['肺心病' in value] for value in case]
df['高血压'] = [[0, 17]['高血压' in value] for value in case]
df['冠心病'] = [[0, 10]['冠心病' in value] for value in case]
df['挂号'] = [[0, 7]['挂号' in value] for value in case]
df['门特挂号'] = [[0, 13]['门特挂号' in value] for value in case]
df['糖尿病'] = [[0, 45]['糖尿病' in value] for value in case]
df['尿毒症'] = [[0, 5]['尿毒症' in value] for value in case]
df['偏瘫'] = [[0, 14]['偏瘫' in value] for value in case]
df['精神病'] = [[0, 2]['精神病' in value] for value in case]
df['是否残疾军人'] = 0
df.loc[(~df['残疾军人医疗补助基金支付金额'].isnull()) | (df['残疾军人医疗补助基金支付金额'] != 0),
'是否残疾军人'] = 1
df['是否城乡救助'] = 0
df.loc[(~df['城乡救助补助金额'].isnull()) | (df['城乡救助补助金额'] != 0), '是否城乡救助'] = 6
df['是否公务员'] = 0
df.loc[(~df['公务员医疗补助基金支付金额'].isnull()) | (df['公务员医疗补助基金支付金额'] != 0),
'是否公务员'] = 4
df['是否自负'] = 0
df.loc[(~df['起付标准以上自负比例金额'].isnull()) | (df['起付标准以上自负比例金额'] != 0),
'是否自负'] = 1
df['是否民政救助'] = 0
df.loc[(~df['民政救助补助金额'].isnull()) | (df['民政救助补助金额'] != 0), '是否民政救助'] = 4
df['是否城乡优抚'] = 0
df.loc[(~df['城乡优抚补助金额'].isnull()) | (df['城乡优抚补助金额'] != 0), '是否城乡优抚'] = 3
# 诊断结果分隔符数量提取
df['case_has_type1'] = [len(value.split(',')) - 1 for value in case]
df['case_has_type2'] = [len(value.split('，')) - 1 for value in case]
df['case_has_type3'] = [len(value.split(';')) - 1 for value in case]
df['case_has_type4'] = [len(value.split('；')) - 1 for value in case]
df['case_has_type5'] = [len(value.split('（')) - 1 for value in case]
df['case_has_type6'] = [len(value.split(' ')) - 1 for value in case]
# 统计信息
case_col1 = [
'心脏病', '肺心病', '高血压', '冠心病', '挂号', '门特挂号', '糖尿病', '尿毒症', '偏瘫', '精神病'
]
case_col_sp = ['是否残疾军人', '是否城乡救助', '是否公务员', '是否自负', '是否民政救助', '是否城乡优抚']
df['病_sum'] = df[case_col1].sum(axis=1)
df['special_sum'] = df[case_col_sp].sum(axis=1)
case_col2 = ['case_length','case_has_type1','case_has_type2','case_has_type3',\
'case_has_type4','case_has_type5','case_has_type6','病_sum', 'special_sum']
money = []
no_money = []
for value in df.columns.values:
if '金额' in value:
money.append(value)
else:
no_money.append(value)
# 非负矩阵分解，得到用户矩阵和项目费用矩阵，将用户矩阵作为新的特征 (20维)
money_sum_df, money_mean_df = df.groupby(['uid'])[money].apply(
np.sum).fillna(0), df.groupby(['uid'])[money].apply(np.mean).fillna(0)
matdfs = {'MoneySum': money_sum_df, 'MoneyMean': money_mean_df}
matvs = {k: item.copy().values for k, item in matdfs.items()}
factor_num = 20
for k in matdfs:
matdf, matv = matdfs[k], matvs[k]
shape = matv.shape
np.random.seed(20)
initW, initH = np.random.rand(shape[0], factor_num), np.random.rand(
factor_num, shape[1])
outW, outH = nmf(matv, initW, initH, 0.0001, 5555555, 250)
feature_factor = pd.DataFrame(
outW,
index=pd.Index(data=matdf.index.values, copy=True, name='uid'),
columns=[k + '_factor_' + str(i)
for i in range(factor_num)]).reset_index()
print(feature_factor.max(axis=0))
feature = pd.merge(feature, feature_factor, on='uid',
how='left').fillna(0)
# 获得用户记录条数
Log('get record number feature...')
feature_rec = df.groupby(['uid'])['顺序号'].count()
feature_rec = feature_rec.rename('record_num')
feature_rec = feature_rec.reset_index()
feature = pd.merge(feature, feature_rec, on='uid', how='left')
# 获得用户去的不同医院数量
Log('get category feature...')
feature_cat = df.groupby(['uid'])['医院编码'].nunique()
feature_cat = feature_cat.rename('hospital_num')
feature_cat = feature_cat.reset_index()
feature = pd.merge(feature, feature_cat, on='uid', how='left')
# 对连续型变量产生统计信息【mean, sum, median, min, max, std】
Log('get continuous feature...')
col_con = money + case_col2
# col_con.append('医疗救助医院申请')
# ,'医疗救助医院申请'
feature_con = df.groupby(['uid'])[col_con].agg(
[np.mean, np.sum, np.median, np.min, np.max, np.std])
feature_con = feature_con.reset_index()
feature = pd.merge(feature, feature_con, on='uid', how='left')
# 对类别变量产生统计信息【mean, sum, std】
Log('get dummy feature...')
feature_dum = df.groupby(['uid'])[case_col1 + case_col_sp].agg(
[np.mean, np.sum, np.std])
feature_dum = feature_dum.reset_index()
feature = pd.merge(feature, feature_dum, on='uid', how='left')
# 非负矩阵分解，得到用户矩阵和医院矩阵，将用户矩阵作为新的特征 (15维)
factor_num = 15
PH_Mat = df.groupby(['uid', '医院编码']).size().unstack().fillna(0)
PH_MatV = PH_Mat.copy().values
shape = PH_MatV.shape
np.random.seed(20)
initW, initH = np.random.rand(shape[0], factor_num), np.random.rand(
factor_num, shape[1])
outW, outH = nmf(PH_MatV, initW, initH, 0.0001, 5555555, 200)
feature_factor = pd.DataFrame(
outW,
index=pd.Index(data=PH_Mat.index.values, copy=True, name='uid'),
columns=['Hostpital_factor_' + str(i)
for i in range(factor_num)]).reset_index()
feature = pd.merge(feature, feature_factor, on='uid', how='left').fillna(0)
return feature
def cluster():
return nmf.nmf();
[5, 3, 0, 1],
[4, 0, 0, 1],
[1, 1, 0, 5],
[1, 0, 0, 4],
[0, 1, 5, 4],
]
V = [
[1, 1, 0, 1, 1],
[1, 0, 0, 1, 0],
[1, 1, 0, 1, 0],
[1, 0, 0, 1, 0],
[0, 1, 1, 1, 0],
]
V = numpy.array(V)
print("V = ")
print(V)
time_start = time.time()
K = 2
W, H = nmf.nmf(V, K)
time_end = time.time()
estimatedV = numpy.dot(W, H)
print("W = ")
print(W)
print("H = ")
print(H)
print("estimatedV = ")
print(estimatedV)
print(time_end - time_start)
# Example data - impute to replace missing values
data = Orange.data.Table("yeast-class-RPR")
imputer = Orange.feature.imputation.MinimalConstructor()
imputer = imputer(data)
data = imputer(data)
# Convert to numpy and separate positive and negative values
# Note that NMF works on strictly *nonnegative data*
X, y, _ = data.to_numpy()
Xp = X * (X > 0)
Xn = X * (X < 0) * (-1)
X = np.hstack([Xp, Xn])
# Unsupervised learning of training examples
W, Hs = nmf([X], rank=rank)
Xa = W.dot(Hs[0])
print Xa.shape
plt.figure(figsize=(5.0, 5.0))
plt.imshow(X)
plt.title("Original")
plt.figure(figsize=(5.0, 5.0))
plt.title("Approximation")
plt.imshow(Xa)
# Show clusters
if show_features:
plt.figure()
plt.title("Clusters")
# Example data - impute to replace missing values
data = Orange.data.Table("yeast-class-RPR")
imputer = Orange.feature.imputation.MinimalConstructor()
imputer = imputer(data)
data = imputer(data)
# Convert to numpy and separate positive and negative values
# Note that NMF works on strictly *nonnegative data*
X, y, _ = data.to_numpy()
Xp = X * (X > 0)
Xn = X * (X < 0) * (-1)
X = np.hstack([Xp, Xn])
# Unsupervised learning of training examples
W, Hs = nmf([X], rank=rank)
Xa = W.dot(Hs[0])
print Xa.shape
plt.figure(figsize=(5.0, 5.0))
plt.imshow(X)
plt.title("Original")
plt.figure(figsize=(5.0, 5.0))
plt.title("Approximation")
plt.imshow(Xa)
# Show clusters
if show_features:
plt.figure()
plt.title("Clusters")
show_features = 0
# Example data - impute to replace missing values
data = Orange.data.Table("yeast-class-RPR")
imputer = Orange.feature.imputation.MinimalConstructor()
imputer = imputer(data)
data = imputer(data)
# Convert to numpy and separate positive and negative values
# Note that NMF works on strictly *nonnegative data*
X, y, _ = data.to_numpy()
Xp = X * (X > 0)
Xn = X * (X < 0) * (-1)
X = np.hstack([Xp, Xn])
# Reshape and select target class
y = y.reshape((len(X), 1))
y = (y == 0).astype(int)
# Learn the model parameters given the attributes and the class values
tr = range(0, len(X), 2)
te = range(1, len(X), 2)
W, Hs = nmf([X[tr], y[tr]], rank=rank)
Wte = nmf_fix([X[te]], [Hs[0]], rank=rank)
prediction = Wte.dot(Hs[1])
# Measure performance
auc = roc_auc_score(y_score=prediction, y_true=y[te])
print "AUC: ", auc
data = Orange.data.Table("yeast-class-RPR")
imputer = Orange.feature.imputation.MinimalConstructor()
imputer = imputer(data)
data = imputer(data)
# Convert to numpy and separate positive and negative values
# Note that NMF works on strictly *nonnegative data*
X, y, _ = data.to_numpy()
Xp = X * (X > 0)
Xn = X * (X < 0) * (-1)
X = np.hstack([Xp, Xn])
# Reshape and select target class
y = y.reshape((len(X), 1))
y = (y == 0).astype(int)
# Learn the model parameters given the attributes and the class values
tr = range(0, len(X), 2)
te = range(1, len(X), 2)
W, Hs = nmf([X[tr], y[tr]], rank=rank)
Wte = nmf_fix([X[te]], [Hs[0]], rank=rank)
prediction = Wte.dot(Hs[1])
# Measure performance
auc = roc_auc_score(y_score=prediction, y_true=y[te])
print "AUC: ", auc
binvals = array.array('f',A.flatten('F').tolist())
binvals.tofile(fp)
fp.close()
return
path = '../data/'
X = npy_from_file(path + 'X.bin')
W = npy_from_file(path + 'W.bin')
H = npy_from_file(path + 'H.bin')
#print X
#print W
#print H
nmf.nmf(X,W,H,100,1)
#print W
#print H
#print np.dot(W,H)
Ay_position_a_guess_llh = xyz2llh(Ay_position_a_guess[0, 0],
Ay_position_a_guess[0, 1],
Ay_position_a_guess[0, 2]).xyz()
F_zhd_a = Mobj_b_base_Error.saastamoinen_model(
np.array([Ay_position_a_guess_llh[0]]),
np.array([Ay_position_a_guess_llh[1]]),
np.array([Ay_position_a_guess_llh[2]]), np.array([np.pi / 2]), 0)
F_zhd_b = Mobj_b_base_Error.saastamoinen_model(
np.array([Ay_position_b_llh[0]]), np.array([Ay_position_b_llh[1]]),
np.array([Ay_position_b_llh[2]]), np.array([np.pi / 2]), 0)
'''
Ay_nmf : b站nmf值
並修正Ay_geographical_distance_a,b
'''
Ay_nmf_b = nmf.nmf(I_doy, Ay_position_b_llh[0], Ay_position_b_llh[1],
Ay_position_b_llh[2], Ay_elevation)
Ay_nmf_a = nmf.nmf(I_doy, Ay_position_a_guess_llh[0],
Ay_position_a_guess_llh[1], Ay_position_a_guess_llh[2],
Ay_elevation)
Ay_geographical_distance_b += F_zhd_b * Ay_nmf_b
Ay_geographical_distance_a += F_zhd_a * Ay_nmf_a
Ay_L1_chose_a_minus_ra = Ay_L1_chose_a - Ay_geographical_distance_a
Ay_C1_chose_a_minus_ra = Ay_C1_chose_a - Ay_geographical_distance_a
Ay_L1_chose_b_minus_rb = Ay_L1_chose_b - Ay_geographical_distance_b
Ay_C1_chose_b_minus_rb = Ay_C1_chose_b - Ay_geographical_distance_b
Ay_L1_chose_SD_minus_rSD = Ay_L1_chose_a_minus_ra - Ay_L1_chose_b_minus_rb
Ay_C1_chose_SD_minus_rSD = Ay_C1_chose_a_minus_ra - Ay_C1_chose_b_minus_rb
def recommend_skill_skill_matrix(user_skills, unique_skills):
n = len(unique_skills.keys())
ss_matrix = np.zeros(n*n).reshape(n,n)
skill_id_map = {}
skill_name_map = {}
skill_id = 0
for sk in unique_skills:
skill_id_map[sk] = skill_id
skill_name_map[skill_id] = sk
skill_id +=1
for sk in user_skills:
for a in range(0,len(sk)):
for b in range(a+1,len(sk)):
s1 = skill_id_map[sk[a]]
s2 = skill_id_map[sk[b]]
ss_matrix[s1][s2] += 1
ss_matrix[s2][s1] += 1
print 'Skill-skill matrix shape', ss_matrix.shape
model = nmf('kl',10)
W,H = model.fit(ss_matrix, 200, False)
ss_matrix_approx = W.dot(H)
print "Reconstructed matrix ", ss_matrix_approx
for sk in skill_id_map:
sid = skill_id_map[sk]
val = ss_matrix_approx[sid,:]
print sk.encode("utf-8"), " : "
top5_h = []
for i in range(5):
max_v = 0
max_j = 0
for j in range(len(val)):
if val[j] > max_v and (j not in top5_h):
max_v = val[j]
max_j = j
top5_h.append(max_j)
val = ss_matrix_approx[:,sid].T
top5_v = []
for i in range(5):
max_v = 0
max_j = 0
for j in range(len(val)):
if val[j] > max_v and (j not in top5_v):
max_v = val[j]
max_j = j
top5_v.append(max_j)
val = ss_matrix[sid,:]
top5_o = []
for i in range(5):
max_v = 0
max_j = 0
for j in range(len(val)):
if val[j] > max_v and (j not in top5_o):
max_v = val[j]
max_j = j
top5_o.append(max_j)
for t1, t2, t3 in zip(top5_o,top5_h,top5_v):
print " ", skill_name_map[t1].encode("utf-8"), " \t", skill_name_map[t2].encode("utf-8")
from numpy import * import numpy as np import nimfa as nm import nmf import plot_err m = 5 n = 5 W = mat(random.random((m, n))) V = np.array([W, W, W]) w2 = mat(random.random((5, 2))) h2 = mat(random.random((5, 2))) (wo, ho) = nmf.nmf(V[:, :, 0], w2, h2, 0.001, 10, 10) print((wo, ho))
binvals = array.array('f',A.flatten('F').tolist())
binvals.tofile(fp)
fp.close()
return
path = '/home/ericb/projects/nmf/trunk/'
X = npy_from_file(path + 'X.bin')
W = npy_from_file(path + 'W.bin')
H = npy_from_file(path + 'H.bin')
#print X
#print W
#print H
nmf.nmf(X,W,H,200,1)
#print W
#print H
#print np.dot(W,H)
