Merge 9174ecc into 229d5dd

.coveragerc

@@ -0,0 +1,2 @@
+[run]
+parallel = True

csrank/choicefunction/generalized_linear_model.py

@@ -203,7 +203,7 @@ def _fit(self, X, Y, sampler='variational', tune=500, draws=500,
     def _predict_scores_fixed(self, X, **kwargs):
         d = dict(pm.summary(self.trace)['mean'])
         intercept = 0.0
-        weights = np.array([d['weights__{}'.format(i)] for i in range(self.n_object_features)])
+        weights = np.array([d['weights[{}]'.format(i)] for i in range(self.n_object_features)])
         if 'intercept' in d:
             intercept = intercept + d['intercept']
         return np.dot(X, weights) + intercept

csrank/dataset_reader/labelranking/survey_dataset_reader.py

@@ -3,7 +3,8 @@
 import numpy as np
 import pandas as pd
 from sklearn.model_selection import ShuffleSplit
-from sklearn.preprocessing import Imputer, StandardScaler
+from sklearn.preprocessing import StandardScaler
+from sklearn.impute import SimpleImputer
 from sklearn.utils import check_random_state
 
 from csrank.constants import LABEL_RANKING
@@ -28,7 +29,7 @@ def __load_dataset__(self):
             context_feature = [float(i) if i != '.' else np.NAN for i in row[13:33]]
             features.append(context_feature)
         X = np.array(features)
-        X = Imputer().fit_transform(X)
+        X = SimpleImputer().fit_transform(X)
         X = np.array([np.log(np.array(X[:, i]) + 1) for i in range(len(features[0]))])
         X = np.array(X.T)
         self.X = StandardScaler().fit_transform(X)

csrank/discretechoice/generalized_nested_logit.py

@@ -283,11 +283,11 @@ def fit(self, X, Y, sampler='variational', tune=500, draws=500,
 
     def _predict_scores_fixed(self, X, **kwargs):
         mean_trace = dict(pm.summary(self.trace)['mean'])
-        weights = np.array([mean_trace['weights__{}'.format(i)] for i in range(self.n_object_features)])
-        lambda_k = np.array([mean_trace['lambda_k__{}'.format(i)] for i in range(self.n_nests)])
+        weights = np.array([mean_trace['weights[{}]'.format(i)] for i in range(self.n_object_features)])
+        lambda_k = np.array([mean_trace['lambda_k[{}]'.format(i)] for i in range(self.n_nests)])
         weights_ik = np.zeros((self.n_object_features, self.n_nests))
         for i, k in product(range(self.n_object_features), range(self.n_nests)):
-            weights_ik[i][k] = mean_trace['weights_ik__{}_{}'.format(i, k)]
+            weights_ik[i][k] = mean_trace['weights_ik[{},{}]'.format(i, k)]
         alpha_ik = np.dot(X, weights_ik)
         alpha_ik = npu.softmax(alpha_ik, axis=2)
         utility = np.dot(X, weights)

csrank/discretechoice/mixed_logit_model.py

@@ -187,7 +187,7 @@ def _predict_scores_fixed(self, X, **kwargs):
         summary = dict(pm.summary(self.trace)['mean'])
         weights = np.zeros((self.n_object_features, self.n_mixtures))
         for i, k in product(range(self.n_object_features), range(self.n_mixtures)):
-            weights[i][k] = summary['weights__{}_{}'.format(i, k)]
+            weights[i][k] = summary['weights[{},{}]'.format(i, k)]
         utility = np.dot(X, weights)
         p = np.mean(npu.softmax(utility, axis=1), axis=2)
         return p

csrank/discretechoice/multinomial_logit_model.py

@@ -181,7 +181,7 @@ def fit(self, X, Y, sampler='variational', tune=500, draws=500,
     def _predict_scores_fixed(self, X, **kwargs):
         d = dict(pm.summary(self.trace)['mean'])
         intercept = 0.0
-        weights = np.array([d['weights__{}'.format(i)] for i in range(self.n_object_features)])
+        weights = np.array([d['weights[{}]'.format(i)] for i in range(self.n_object_features)])
         if 'intercept' in d:
             intercept = intercept + d['intercept']
         return np.dot(X, weights) + intercept

csrank/discretechoice/nested_logit_model.py

@@ -342,9 +342,9 @@ def fit(self, X, Y, sampler='variational', tune=500, draws=500,
     def _predict_scores_fixed(self, X, **kwargs):
         y_nests = self.create_nests(X)
         mean_trace = dict(pm.summary(self.trace)['mean'])
-        weights = np.array([mean_trace['weights__{}'.format(i)] for i in range(self.n_object_features)])
-        weights_k = np.array([mean_trace['weights_k__{}'.format(i)] for i in range(self.n_object_features)])
-        lambda_k = np.array([mean_trace['lambda_k__{}'.format(i)] for i in range(self.n_nests)])
+        weights = np.array([mean_trace['weights[{}]'.format(i)] for i in range(self.n_object_features)])
+        weights_k = np.array([mean_trace['weights_k[{}]'.format(i)] for i in range(self.n_object_features)])
+        lambda_k = np.array([mean_trace['lambda_k[{}]'.format(i)] for i in range(self.n_nests)])
         weights = (weights / lambda_k[:, None])
         utility_k = np.dot(self.features_nests, weights_k)
         utility = self._eval_utility_np(X, y_nests, weights)

csrank/discretechoice/paired_combinatorial_logit.py

@@ -280,8 +280,8 @@ def fit(self, X, Y, sampler='variational', tune=500, draws=500,
 
     def _predict_scores_fixed(self, X, **kwargs):
         mean_trace = dict(pm.summary(self.trace)['mean'])
-        weights = np.array([mean_trace['weights__{}'.format(i)] for i in range(self.n_object_features)])
-        lambda_k = np.array([mean_trace['lambda_k__{}'.format(i)] for i in range(self.n_nests)])
+        weights = np.array([mean_trace['weights[{}]'.format(i)] for i in range(self.n_object_features)])
+        lambda_k = np.array([mean_trace['lambda_k[{}]'.format(i)] for i in range(self.n_nests)])
         utility = np.dot(X, weights)
         p = self._get_probabilities_np(utility, lambda_k)
         return p

requirements.txt

@@ -10,7 +10,7 @@ docopt>=0.6.0
 joblib>=0.9.4
 tqdm>=4.11.2
 keras>=2.3
-pymc3>=3.5
+pymc3>=3.8
 theano>=1.0
 # Pick either CPU or GPU version of tensorflow:
 tensorflow>=1.5,<2.0

scripts/create_testenv.sh

@@ -22,7 +22,8 @@ then
 fi
 
 
-conda install --yes numpy scipy joblib pytest pytest-cov coverage scikit-learn pandas h5py seaborn mkl-service
+conda install --yes numpy scipy joblib pytest pytest-cov pandas h5py seaborn mkl-service
+conda install --yes -c conda-forge coverage=5.0.3
 pip install sphinx sphinx-autobuild nbsphinx pandoc ipykernel bottleneck sphinx_rtd_theme notebook sphinxcontrib-bibtex
 pip install --no-cache-dir --ignore-installed -r requirements.txt