From e81009e665fefe771f820c937febdfbc60783c22 Mon Sep 17 00:00:00 2001
From: Alex Moreo <alejandro.moreo@isti.cnr.it>
Date: Thu, 3 Dec 2020 16:36:54 +0100
Subject: [PATCH] fixing dataset loading

---
 quapy/dataset/__init__.py      |  5 +++--
 quapy/dataset/base.py          |  3 +--
 quapy/dataset/preprocessing.py | 12 ++++++------
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/quapy/dataset/__init__.py b/quapy/dataset/__init__.py
index 0853ddb..e44efa4 100644
--- a/quapy/dataset/__init__.py
+++ b/quapy/dataset/__init__.py
@@ -1,4 +1,5 @@
 from .base import *
-from . import base
-from . import reader
+from .reader import *
 from . import preprocessing
+
+
diff --git a/quapy/dataset/base.py b/quapy/dataset/base.py
index 7086596..29a188f 100644
--- a/quapy/dataset/base.py
+++ b/quapy/dataset/base.py
@@ -1,6 +1,5 @@
 import numpy as np
-from scipy.sparse import issparse, dok_matrix
-from sklearn.feature_extraction.text import TfidfVectorizer
+from scipy.sparse import issparse
 from sklearn.model_selection import train_test_split
 from quapy.functional import artificial_prevalence_sampling
 from scipy.sparse import vstack
diff --git a/quapy/dataset/preprocessing.py b/quapy/dataset/preprocessing.py
index 1db2c27..a6259b2 100644
--- a/quapy/dataset/preprocessing.py
+++ b/quapy/dataset/preprocessing.py
@@ -1,7 +1,7 @@
+import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
 from dataset.base import Dataset
 from scipy.sparse import spmatrix
-import numpy as np
 from utils.util import parallelize
 from .base import LabelledCollection
 
@@ -17,8 +17,8 @@ def text2tfidf(dataset:Dataset, min_df=3, sublinear_tf=True, inplace=False, **kw
     :return: a new Dataset in csr_matrix format (if inplace=False) or a reference to the current Dataset (inplace=True)
     where the instances are stored in a csr_matrix of real-valued tfidf scores
     """
-    __check_type(dataset.training.instances, list, str)
-    __check_type(dataset.test.instances, list, str)
+    __check_type(dataset.training.instances, np.ndarray, str)
+    __check_type(dataset.test.instances, np.ndarray, str)
 
     vectorizer = TfidfVectorizer(min_df=min_df, sublinear_tf=sublinear_tf, **kwargs)
     training_documents = vectorizer.fit_transform(dataset.training.instances)
@@ -45,8 +45,8 @@ def reduce_columns(dataset:Dataset, min_df=5, inplace=False):
     :return: a new Dataset (if inplace=False) or a reference to the current Dataset (inplace=True)
     where the dimensions corresponding to infrequent instances have been removed
     """
-    __check_type(dataset.training, spmatrix)
-    __check_type(dataset.test, spmatrix)
+    __check_type(dataset.training.instances, spmatrix)
+    __check_type(dataset.test.instances, spmatrix)
     assert dataset.training.instances.shape[1] == dataset.test.instances.shape[1], 'unaligned vector spaces'
 
     def filter_by_occurrences(X, W):
@@ -101,7 +101,7 @@ def __check_type(container, container_type=None, element_type=None):
         assert isinstance(container, container_type), \
             f'unexpected type of container (expected {container_type}, found {type(container)})'
     if element_type:
-        assert isinstance(next(container), element_type), \
+        assert isinstance(container[0], element_type), \
             f'unexpected type of element (expected {container_type}, found {type(container)})'