def GetImputedDataframe(self, df, impute_type='mean'):
df = df.copy()
# impute missing values
if impute_type == 'mean':
null_sum = df.replace('?', np.nan).isnull().sum()
null_col = [k for k, v in null_sum.iteritems() if v != 0]
for each_col_ind, each_col in enumerate(self.col_names):
if each_col in null_col and self.col_types[
each_col_ind] != 'str':
df[each_col] = mean_impute(
df, each_col, data_type=self.col_types[each_col_ind])
elif impute_type == 'nnm':
df = df.replace('?', np.nan)
df = pd.DataFrame(NuclearNormMinimization().complete(df),
columns=self.col_names)
else:
raise Exception()
return df
def netPred(self, method='mf', dim=100, alpha=0.1):
'''
supported methods: mf, cf, mnmf, fancy_nnm, fancy_soft
'''
if method == 'mf':
model = NMF(n_components=dim, alpha=alpha, l1_ratio=0.2)
W = model.fit_transform(self.mat)
H = model.components_
self.pred = np.matmul(W, H)
elif method == 'cf':
model = implicit.als.AlternatingLeastSquares(factors=dim,
regularization=alpha)
model.fit(self.mat)
self.pred = np.matmul(model.item_factors, model.user_factors.T)
elif method == 'mnmf':
self.pred = mnmf(self.mat, dim, alpha)
elif 'fancy' in method:
X = self.mat.toarray().astype(np.float)
X[X == 0] = np.nan
if 'nnm' in method:
self.pred = NuclearNormMinimization(
error_tolerance=0.01).complete(X)
elif 'soft' in method:
self.pred = SoftImpute().complete(X)
"f_2551", "f_2552", "f_2553", "f_2554", "f_2555", "f_2556", "f_2557",
"f_2558", "f_2559", "f_2560", "f_2561", "f_2562", "f_2563", "f_2564",
"f_2565", "f_2566", "f_2567", "f_2568", "f_2569", "f_2570", "f_2571",
"f_2572", "f_2573", "f_2574", "f_2575", "f_2576", "f_2577", "f_2578",
"f_2579", "f_2580", "f_2581", "f_2582", "f_2583", "f_2584", "f_2585",
"f_2586", "f_2587", "f_2588", "f_2589", "f_2590", "f_2591", "f_2592",
"f_2593", "f_2594", "f_2595", "f_2596", "f_2597", "f_2598", "f_2599",
"label"
]
if True:
data = read_csv(open('train.csv', 'r'), na_values='').as_matrix()
X1 = data[:, 1:-1] # input features
Y1 = data[:, -1].astype('int') # input features
X1 = NuclearNormMinimization(min_value=0.0, max_value=1.0).complete(X1)
train = np.concatenate((X1, np.reshape(Y1, (-1, 1))), axis=1)
pd.DataFrame(train).to_csv('train_nnm.csv', header=lst)
print('Train done:', train.shape, data.shape)
data = read_csv(open('test.csv', 'r'), na_values='').as_matrix()
X2 = data[:, 1:] # features
train = X1.shape[0]
X = np.concatenate((X1, X2))
del X1, X2
X_net = NuclearNormMinimization(min_value=0.0, max_value=1.0).complete(X)
