likelihood 1.2.25__tar.gz → 1.3.0__tar.gz

{likelihood-1.2.25 → likelihood-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: likelihood
-Version: 1.2.25
+Version: 1.3.0
 Summary: A package that performs the maximum likelihood algorithm.
 Home-page: https://github.com/jzsmoreno/likelihood/
 Author: J. A. Moreno-Guerra

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood/graph/graph.py

@@ -45,8 +45,8 @@ class DynamicGraph(FeatureSelection):
 
     def draw(self, name="graph.html", **kwargs) -> None:
         """Display the network using HTML format"""
-        spring_length = kwargs["spring_length"] if "spring_length" in kwargs else 500
-        node_distance = kwargs["node_distance"] if "node_distance" in kwargs else 100
+        spring_length = kwargs.get("spring_length", 500)
+        node_distance = kwargs.get("node_distance", 100)
         self.G.repulsion(node_distance=node_distance, spring_length=spring_length)
         self.G.show_buttons(filter_=["physics"])
         self.G.show(name)
@@ -89,5 +89,5 @@ if __name__ == "__main__":
     df["y"] = y
     # Instantiate DynamicGraph
     fs = DynamicGraph(df, n_importances=2)
-    print(fs.fit())
+    fs.fit()
     fs.draw()

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood/graph/nn.py

@@ -96,7 +96,7 @@ def cal_adjacency_matrix(
 
     assert len(df_categorical) > 0
 
-    similarity = kwargs["similarity"] if "similarity" in kwargs else len(df_categorical.columns) - 1
+    similarity = kwargs.get("similarity", len(df_categorical.columns) - 1)
     assert similarity <= df_categorical.shape[1]
 
     adj_dict = {}

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood/models/deep/autoencoders.py

@@ -79,6 +79,8 @@ class AutoClassifier(tf.keras.Model):
             The activation function to use for the classifier layer. Default is "softmax". If the activation function is not a classification function, the model can be used in regression problems.
         num_layers : `int`
             The number of hidden layers in the classifier. Default is 1.
+        dropout : `float`
+            The dropout rate to use in the classifier. Default is None.
         """
         super(AutoClassifier, self).__init__()
         self.input_shape_parm = input_shape_parm
@@ -91,6 +93,7 @@ class AutoClassifier(tf.keras.Model):
         self.classifier = None
         self.classifier_activation = kwargs.get("classifier_activation", "softmax")
         self.num_layers = kwargs.get("num_layers", 1)
+        self.dropout = kwargs.get("dropout", None)
 
     def build(self, input_shape):
         self.encoder = tf.keras.Sequential(
@@ -113,6 +116,8 @@ class AutoClassifier(tf.keras.Model):
                 self.classifier.add(
                     tf.keras.layers.Dense(units=self.units, activation=self.activation)
                 )
+                if self.dropout:
+                    self.classifier.add(tf.keras.layers.Dropout(self.dropout))
         self.classifier.add(
             tf.keras.layers.Dense(units=self.num_classes, activation=self.classifier_activation)
         )
@@ -132,6 +137,7 @@ class AutoClassifier(tf.keras.Model):
             "activation": self.activation,
             "classifier_activation": self.classifier_activation,
             "num_layers": self.num_layers,
+            "dropout": self.dropout,
         }
         base_config = super(AutoClassifier, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
@@ -145,6 +151,7 @@ class AutoClassifier(tf.keras.Model):
             activation=config["activation"],
             classifier_activation=config["classifier_activation"],
             num_layers=config["num_layers"],
+            dropout=config["dropout"],
         )
 
 
@@ -156,6 +163,7 @@ def call_existing_code(
     input_shape_parm: None | int = None,
     num_classes: None | int = None,
     num_layers: int = 1,
+    **kwargs,
 ) -> AutoClassifier:
     """
     Calls an existing AutoClassifier instance.
@@ -180,12 +188,14 @@ def call_existing_code(
     `AutoClassifier`
         The AutoClassifier instance.
     """
+    dropout = kwargs.get("dropout", None)
     model = AutoClassifier(
         input_shape_parm=input_shape_parm,
         num_classes=num_classes,
         units=units,
         activation=activation,
         num_layers=num_layers,
+        dropout=dropout,
     )
     model.compile(
         optimizer=optimizer,
@@ -254,6 +264,11 @@ def build_model(
         if "num_layers" not in hyperparameters_keys
         else hyperparameters["num_layers"]
     )
+    dropout = (
+        hp.Float("dropout", min_value=0.1, max_value=0.9, sampling="log")
+        if "dropout" not in hyperparameters_keys
+        else hyperparameters["dropout"]
+    )
 
     model = call_existing_code(
         units=units,
@@ -263,6 +278,7 @@ def build_model(
         input_shape_parm=input_shape_parm,
         num_classes=num_classes,
         num_layers=num_layers,
+        dropout=dropout,
     )
     return model
 
@@ -408,10 +424,8 @@ class GetInsights:
         self.model = model
         self.encoder_layer = self.model.encoder.layers[0]
         self.decoder_layer = self.model.decoder.layers[0]
-        self.classifier_layer = self.model.classifier.layers[-2]
         self.encoder_weights = self.encoder_layer.get_weights()[0]
         self.decoder_weights = self.decoder_layer.get_weights()[0]
-        self.classifier_weights = self.classifier_layer.get_weights()[0]
         colors = dict(mcolors.BASE_COLORS, **mcolors.CSS4_COLORS)
 
         by_hsv = sorted(
@@ -580,7 +594,12 @@ if __name__ == "__main__":
     y = np.asarray(y).astype(np.float32)
 
     model = AutoClassifier(
-        input_shape_parm=X.shape[1], num_classes=3, units=27, activation="selu", num_layers=2
+        input_shape_parm=X.shape[1],
+        num_classes=3,
+        units=27,
+        activation="tanh",
+        num_layers=2,
+        dropout=0.2,
     )
     model.compile(
         optimizer="adam",

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood/models/simulation.py

@@ -2,31 +2,25 @@ import pickle
 import warnings
 from typing import List, Tuple, Union
 
-import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 from pandas.core.frame import DataFrame
 
 from likelihood.tools import DataScaler, FeatureSelection, OneHotEncoder, cdf, check_nan_inf
 
-# Suppress RankWarning
 warnings.simplefilter("ignore", np.RankWarning)
 
 
 # --------------------------------------------------------------------------------------------------------------------------------------
 def categories_by_quartile(df: DataFrame, column: str) -> Tuple[str, str]:
-    # Count the frequency of each category in the column
     freq = df[column].value_counts()
 
-    # Calculate the 25th percentile (Q1) and 75th percentile (Q3)
     q1 = freq.quantile(0.25)
     q3 = freq.quantile(0.75)
 
-    # Filter categories that are below the 25th percentile and above the 75th percentile
     least_frequent = freq[freq <= q1]
     most_frequent = freq[freq >= q3]
 
-    # Get the least frequent category (25th percentile) and the most frequent category (75th percentile)
     least_frequent_category = least_frequent.idxmin() if not least_frequent.empty else None
     most_frequent_category = most_frequent.idxmax() if not most_frequent.empty else None
 

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood/models/utils.py

@@ -1,12 +1,10 @@
-import matplotlib.pyplot as plt
 import numpy as np
-from numpy import ndarray
 
 from likelihood.tools import cal_average
 
 
 class FeaturesArima:
-    def forward(self, y_sum: ndarray, theta: list, mode: bool, noise: float):
+    def forward(self, y_sum: np.ndarray, theta: list, mode: bool, noise: float):
         if mode:
             y_vec = []
 
@@ -31,20 +29,14 @@ class FeaturesArima:
 
         return np.array(y_vec)
 
-    def integrated(self, datapoints: ndarray):
+    def integrated(self, datapoints: np.ndarray):
         datapoints = self.datapoints
-        # n = datapoints.shape[0]
-
-        # y_sum = [
-        #    ((1.0 - datapoints[i - 1] / datapoints[i]) ** self.d) * datapoints[i]
-        #    for i in range(1, n)
-        # ]
         y_sum = list(np.diff(datapoints, self.d))
         y_sum.insert(0, datapoints[0])
 
         return np.array(y_sum)
 
-    def average(self, datapoints: ndarray):
+    def average(self, datapoints: np.ndarray):
         y_sum_average = cal_average(datapoints)
         y_sum_eps = datapoints - y_sum_average
 

{likelihood-1.2.25 → likelihood-1.3.0}/likelihood.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: likelihood
-Version: 1.2.25
+Version: 1.3.0
 Summary: A package that performs the maximum likelihood algorithm.
 Home-page: https://github.com/jzsmoreno/likelihood/
 Author: J. A. Moreno-Guerra