Remake of the documentation (#413)

asreview · Nov 18, 2020 · 4ca41f9 · 4ca41f9
1 parent 2d2f232
commit 4ca41f9
Show file tree

Hide file tree

Showing 85 changed files with 1,709 additions and 654 deletions.
diff --git a/asreview/data.py b/asreview/data.py
@@ -88,7 +88,7 @@ def get_fuzzy_scores(keywords, match_strings):
 
     Returns
     -------
-    np.ndarray:
+    numpy.ndarray
         Array of scores ordered in the same way as the str_list input.
     """
     return token_set_ratio(keywords, match_strings)
@@ -99,7 +99,7 @@ class ASReviewData():
 
     Arguments
     ---------
-    df: pd.DataFrame
+    df: pandas.DataFrame
         Dataframe containing the data for the ASReview data object.
     data_name: str
         Give a name to the data object.
@@ -168,12 +168,12 @@ def slice(self, idx, by_index=True):
 
         Arguments
         ---------
-        idx: list, np.ndarray
+        idx: list, numpy.ndarray
             Record ids that should be kept.
 
         Returns
         -------
-        ASReviewData:
+        ASReviewData
             Slice of itself.
         """
         if self.df is None:
@@ -242,9 +242,9 @@ def from_file(cls, fp, read_fn=None, data_name=None, data_type=None):
 
         Arguments
         ---------
-        fp: str, Path
+        fp: str, pathlib.Path
             Read the data from this file.
-        read_fn: function
+        read_fn: callable
             Function to read the file. It should return a standardized
             dataframe.
         data_name: str
@@ -300,7 +300,7 @@ def record(self, i, by_index=True):
 
         Returns
         -------
-        PaperRecord:
+        PaperRecord
             The corresponding record if i was an integer, or a list of records
             if i was an iterable.
         """
@@ -376,15 +376,16 @@ def fuzzy_find(self,
             Don't return records below this threshold.
         max_return: int
             Maximum number of records to return.
-        exclude: list, np.ndarray
+        exclude: list, numpy.ndarray
             List of indices that should be excluded in the search. You would
             put papers that were already labeled here for example.
         by_index: bool
             If True, use internal indexing.
             If False, use record ids for indexing.
+
         Returns
         -------
-        list:
+        list
             Sorted list of indexes that match best the keywords.
         """
         new_ranking = get_fuzzy_scores(keywords, self.match_string)
@@ -528,7 +529,7 @@ def prior_labels(self, state, by_index=True):
 
         Returns
         -------
-        np.array:
+        numpy.ndarray
             Array of indices that have the 'initial' property.
         """
         query_src = state.startup_vals()["query_src"]
@@ -552,9 +553,9 @@ def to_file(self, fp, labels=None, ranking=None):
         ---------
         fp: str
             Filepath to export to.
-        labels: list, np.array
+        labels: list, numpy.ndarray
             Labels to be inserted into the dataframe before export.
-        ranking: list, np.array
+        ranking: list, numpy.ndarray
             Optionally, dataframe rows can be reordered.
         """
         if Path(fp).suffix in [".csv", ".CSV"]:
@@ -573,7 +574,7 @@ def to_dataframe(self, labels=None, ranking=None):
 
         Arguments
         ---------
-        labels: list, np.ndarray
+        labels: list, numpy.ndarray
             Current labels will be overwritten by these labels
             (including unlabelled). No effect if labels is None.
         ranking: list
@@ -582,7 +583,7 @@ def to_dataframe(self, labels=None, ranking=None):
 
         Returns
         -------
-        pd.DataFrame:
+        pandas.DataFrame
             Dataframe of all available record data.
         """
         new_df = pd.DataFrame.copy(self.df)
@@ -607,7 +608,7 @@ def to_csv(self, fp, labels=None, ranking=None):
         ---------
         fp: str, NoneType
             Filepath or None for buffer.
-        labels: list, np.ndarray
+        labels: list, numpy.ndarray
             Current labels will be overwritten by these labels
             (including unlabelled). No effect if labels is None.
         ranking: list
@@ -616,7 +617,7 @@ def to_csv(self, fp, labels=None, ranking=None):
 
         Returns
         -------
-        pd.DataFrame:
+        pandas.DataFrame
             Dataframe of all available record data.
         """
         df = self.to_dataframe(labels=labels, ranking=ranking)
@@ -629,7 +630,7 @@ def to_excel(self, fp, labels=None, ranking=None):
         ---------
         fp: str, NoneType
             Filepath or None for buffer.
-        labels: list, np.ndarray
+        labels: list, numpy.ndarray
             Current labels will be overwritten by these labels
             (including unlabelled). No effect if labels is None.
         ranking: list
@@ -638,7 +639,7 @@ def to_excel(self, fp, labels=None, ranking=None):
 
         Returns
         -------
-        pd.DataFrame:
+        pandas.DataFrame
             Dataframe of all available record data.
         """
         df = self.to_dataframe(labels=labels, ranking=ranking)

diff --git a/asreview/io/utils.py b/asreview/io/utils.py
@@ -58,7 +58,7 @@ def standardize_dataframe(df, column_spec={}):
 
     Arguments
     ---------
-    df: pd.DataFrame
+    df: pandas.DataFrame
         Unclean dataframe to be cleaned up.
 
     Returns

diff --git a/asreview/models/balance/base.py b/asreview/models/balance/base.py
@@ -27,18 +27,18 @@ def sample(self, X, y, train_idx, shared):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Complete feature matrix.
-        y: np.array
+        y: numpy.ndarray
             Labels for all papers.
-        train_idx: np.array
+        train_idx: numpy.ndarray
             Training indices, that is all papers that have been reviewed.
         shared: dict
             Dictionary to share data between balancing models and other models.
 
         Returns
         -------
-        np.array, np.array:
+        numpy.ndarray, numpy.ndarray
             X_train, y_train: the resampled matrix, labels.
         """
         raise NotImplementedError
diff --git a/asreview/models/balance/double.py b/asreview/models/balance/double.py
@@ -69,18 +69,18 @@ def sample(self, X, y, train_idx, shared):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Complete feature matrix.
-        y: np.array
+        y: numpy.ndarray
             Labels for all papers.
-        train_idx: np.array
+        train_idx: numpy.ndarray
             Training indices, that is all papers that have been reviewed.
         shared: dict
             Dictionary to share data between balancing models and other models.
 
         Returns
         -------
-        np.array, np.array:
+        numpy.ndarray,numpy.ndarray:
             X_train, y_train: the resampled matrix, labels.
         """
         # Get inclusions and exclusions

diff --git a/asreview/models/balance/simple.py b/asreview/models/balance/simple.py
@@ -29,18 +29,18 @@ def sample(self, X, y, train_idx, shared):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Complete matrix of all samples.
-        y: np.array
+        y: numpy.ndarray
             Classified results of all samples.
         extra_vars: dict:
             Extra variables that can be passed around between functions.
 
         Returns
         -------
-        np.array:
+        numpy.ndarray:
             Training samples.
-        np.array:
+        numpy.ndarray:
             Classification of training samples.
         """
         return X[train_idx], y[train_idx]
diff --git a/asreview/models/balance/triple.py b/asreview/models/balance/triple.py
@@ -90,18 +90,18 @@ def sample(self, X, y, train_idx, shared):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Complete feature matrix.
-        y: np.array
+        y: numpy.ndarray
             Labels for all papers.
-        train_idx: np.array
+        train_idx: numpy.ndarray
             Training indices, that is all papers that have been reviewed.
         shared: dict
             Dictionary to share data between balancing models and other models.
 
         Returns
         -------
-        np.array, np.array:
+        numpy.ndarray,numpy.ndarray:
             X_train, y_train: the resampled matrix, labels.
         """
         max_idx = np.array(shared["query_src"].get("max", []), dtype=np.int)

diff --git a/asreview/models/balance/undersample.py b/asreview/models/balance/undersample.py
@@ -46,18 +46,18 @@ def sample(self, X, y, train_idx, shared):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Complete feature matrix.
-        y: np.array
+        y: numpy.ndarray
             Labels for all papers.
-        train_idx: np.array
+        train_idx: numpy.ndarray
             Training indices, that is all papers that have been reviewed.
         shared: dict
             Dictionary to share data between balancing models and other models.
 
         Returns
         -------
-        np.array, np.array:
+        numpy.ndarray,numpy.ndarray:
             X_train, y_train: the resampled matrix, labels.
         """
         one_ind = train_idx[np.where(y[train_idx] == 1)]

diff --git a/asreview/models/base.py b/asreview/models/base.py
@@ -37,7 +37,7 @@ def default_param(self):
 
         Returns
         -------
-        dict:
+        dict
             Dictionary with parameter: default value
         """
         cur_class = self.__class__
@@ -55,7 +55,7 @@ def param(self):
 
         Returns
         -------
-        dict:
+        dict
             Dictionary with parameter: current value.
         """
         parameters = self.default_param

diff --git a/asreview/models/classifiers/base.py b/asreview/models/classifiers/base.py
@@ -36,9 +36,11 @@ def __init__(self):
     def fit(self, X, y):
         """Fit the model to the data.
 
-        X: np.array
+        Arguments
+        ---------
+        X: numpy.ndarray
             Feature matrix to fit.
-        y: np.array
+        y: numpy.ndarray
             Labels for supervised learning.
         """
         return self._model.fit(X, y)
@@ -48,12 +50,12 @@ def predict_proba(self, X):
 
         Arguments
         ---------
-        X: np.array
+        X: numpy.ndarray
             Feature matrix to predict.
 
         Returns
         -------
-        np.array:
+        numpy.ndarray
             Array with the probabilities for each class, with two
             columns (class 0, and class 1) and the number of samples rows.
         """
@@ -64,10 +66,8 @@ def full_hyper_space(self):
 
         Returns
         -------
-        dict:
-            Parameter space.
-        dict:
-            Parameter choices; in case of hyperparameters with a list of
-            choices, store the choices there.
+        dict, dict
+            Parameter space. Parameter choices; in case of hyperparameters
+            with a list of choices, store the choices there.
         """
         return {}, {}
diff --git a/asreview/models/classifiers/lstm_base.py b/asreview/models/classifiers/lstm_base.py
@@ -58,7 +58,7 @@ class LSTMBaseClassifier(BaseTrainClassifier):
 
     Arguments
     ---------
-    embedding_matrix: np.array
+    embedding_matrix: numpy.ndarray
         Embedding matrix to use with LSTM model.
     backwards: bool
         Whether to have a forward or backward LSTM.

diff --git a/asreview/models/classifiers/lstm_pool.py b/asreview/models/classifiers/lstm_pool.py
@@ -62,7 +62,7 @@ class LSTMPoolClassifier(BaseTrainClassifier):
 
     Arguments
     ---------
-    embedding_matrix: np.array
+    embedding_matrix: numpy.ndarray
         Embedding matrix to use with LSTM model.
     backwards: bool
         Whether to have a forward or backward LSTM.

diff --git a/asreview/models/feature_extraction/base.py b/asreview/models/feature_extraction/base.py
@@ -18,12 +18,12 @@ def fit_transform(self, texts, titles=None, abstracts=None, keywords=None):
 
         Arguments
         ---------
-        texts: np.array
+        texts: numpy.ndarray
             A sequence of texts to be transformed. They are not yet tokenized.
 
         Returns
         -------
-        np.array:
+        numpy.ndarray
             Feature matrix representing the texts.
         """
         self.fit(texts)
@@ -53,13 +53,12 @@ def fit_transform(self, texts, titles=None, abstracts=None, keywords=None):
     def fit(self, texts):
         """Fit the model to the texts.
 
-
         It is not always necessary to implement this if there's not real
         fitting being done.
 
         Arguments
         ---------
-        texts: np.array
+        texts: numpy.ndarray
             Texts to be fitted.
         """
         pass
@@ -70,12 +69,12 @@ def transform(self, texts):
 
         Arguments
         ---------
-        texts: np.array
+        texts: numpy.ndarray
             A sequence of texts to be transformed. They are not yet tokenized.
 
         Returns
         -------
-        np.array:
+        numpy.ndarray
             Feature matrix representing the texts.
         """
         raise NotImplementedError