likelihood 1.5.7__py3-none-any.whl → 2.0.0__py3-none-any.whl

likelihood/tools/cat_embed.py

@@ -0,0 +1,213 @@
+import logging
+import os
+from typing import List
+
+import numpy as np
+import pandas as pd
+
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+logging.getLogger("tensorflow").setLevel(logging.ERROR)
+import tensorflow as tf
+from pandas.core.frame import DataFrame
+from sklearn.preprocessing import LabelEncoder
+
+tf.get_logger().setLevel("ERROR")
+
+
+class CategoricalEmbedder:
+    def __init__(self, embedding_dim=32):
+        self.embedding_dim = embedding_dim
+        self.label_encoders = {}
+        self.embeddings = {}
+
+    def fit(self, df: DataFrame, categorical_cols: List):
+        """
+        Fit the embeddings on the given data.
+
+        Parameters
+        ----------
+        df : `DataFrame`
+            Pandas DataFrame containing the tabular data.
+        categorical_cols : `List`
+            List of column names representing categorical features.
+
+        Returns
+        -------
+        `None`
+        """
+        df_processed = df.copy()
+        for col in categorical_cols:
+            if col not in df_processed.columns:
+                raise ValueError(f"Column {col} not found in DataFrame")
+
+        for col in categorical_cols:
+            mode_val = df_processed[col].mode()
+            if not mode_val.empty:
+                df_processed[col] = df_processed[col].fillna(mode_val[0])
+
+        for col in categorical_cols:
+            le = LabelEncoder()
+            df_processed[col] = le.fit_transform(df_processed[col])
+            self.label_encoders[col] = le
+
+            vocab_size = len(le.classes_)
+            embedding_matrix = np.random.rand(vocab_size, self.embedding_dim)
+            self.embeddings[col] = tf.Variable(embedding_matrix, dtype=tf.float32)
+
+    def transform(self, df: DataFrame, categorical_cols: List[str]):
+        """
+        Transform the data using the fitted embeddings.
+
+        Parameters
+        ----------
+        df : `DataFrame`
+            Pandas DataFrame containing the tabular data.
+        categorical_cols : `List[str]`
+            List of column names representing categorical features.
+
+        Returns
+        -------
+        Transformed Pandas DataFrame with original columns except `categorical_cols` replaced by their embedding representations.
+        """
+
+        df_processed = df.copy()
+
+        for col in categorical_cols:
+            if col not in self.label_encoders:
+                raise ValueError(
+                    f"Column {col} has not been fitted. Please call fit() on this column first."
+                )
+            mode_val = df_processed[col].mode()
+            if not mode_val.empty:
+                df_processed[col] = df_processed[col].fillna(mode_val[0])
+            le = self.label_encoders[col]
+            df_processed[col] = le.transform(df_processed[col])
+
+        for col in categorical_cols:
+            indices_tensor = tf.constant(df_processed[col], dtype=tf.int32)
+            embedding_layer = tf.nn.embedding_lookup(
+                params=self.embeddings[col], ids=indices_tensor
+            )
+            if len(embedding_layer.shape) == 1:
+                embedding_layer = tf.expand_dims(embedding_layer, axis=0)
+
+            for i in range(self.embedding_dim):
+                df_processed[f"{col}_embed_{i}"] = embedding_layer[:, i]
+            df_processed.drop(columns=[col], inplace=True)
+
+        return df_processed
+
+    def inverse_transform(self, df: pd.DataFrame, categorical_cols: List[str]):
+        """
+        Inverse transform the data using the fitted embeddings.
+
+        Parameters
+        ----------
+        df : `DataFrame`
+            Pandas DataFrame containing the tabular data with embedded representations.
+        categorical_cols : `List[str]`
+            List of column names representing categorical features.
+
+        Returns
+        -------
+        Transformed Pandas DataFrame with original columns replaced by their categorical labels.
+        """
+
+        df_processed = df.copy()
+
+        for col in categorical_cols:
+            if col not in self.label_encoders:
+                raise ValueError(
+                    f"Column {col} has not been fitted. Please call fit() on this column first."
+                )
+
+            embedding_matrix = self.embeddings[col].numpy()
+            label_encoder = self.label_encoders[col]
+
+            embedded_columns = [f"{col}_embed_{i}" for i in range(self.embedding_dim)]
+            embeddings = df_processed[embedded_columns].values
+
+            distances = np.linalg.norm(embedding_matrix - embeddings[:, np.newaxis], axis=2)
+            original_indices = np.argmin(distances, axis=1)
+            original_labels = label_encoder.inverse_transform(original_indices)
+
+            df_processed[col] = original_labels
+            df_processed.drop(columns=embedded_columns, inplace=True)
+
+        return df_processed
+
+    def save_embeddings(self, path: str):
+        """
+        Save the embeddings to a directory.
+
+        Parameters
+        ----------
+        path : `str`
+            Path to the directory where embeddings will be saved.
+        """
+
+        os.makedirs(path, exist_ok=True)
+        for col, embedding in self.embeddings.items():
+            np.save(os.path.join(path, f"{col}_embedding.npy"), embedding.numpy())
+
+    def load_embeddings(self, path: str):
+        """
+        Load the embeddings from a directory.
+
+        Parameters
+        ----------
+        path : `str`
+            Path to the directory where embeddings are saved.
+        """
+
+        for col in self.label_encoders.keys():
+            embedding_path = os.path.join(path, f"{col}_embedding.npy")
+            if not os.path.exists(embedding_path):
+                raise FileNotFoundError(f"Embedding file {embedding_path} not found.")
+            embedding_matrix = np.load(embedding_path)
+            self.embeddings[col] = tf.Variable(embedding_matrix, dtype=tf.float32)
+
+
+if __name__ == "__main__":
+    data = {
+        "color": ["red", "blue", None, "green", "blue"],
+        "size": ["S", "M", "XL", "XS", None],
+        "price": [10.99, 25.50, 30.00, 8.75, 12.25],
+    }
+    df = pd.DataFrame(data)
+
+    # Initialize the embedder
+    embedder = CategoricalEmbedder(embedding_dim=3)
+
+    # Fit the embeddings on the data
+    embedder.fit(df, categorical_cols=["color", "size"])
+
+    # Transform the data using the fitted embeddings
+    processed_df = embedder.transform(df, categorical_cols=["color", "size"])
+
+    print("Processed DataFrame:")
+    print(processed_df.head())
+
+    # Save the embeddings to disk
+    embedder.save_embeddings("./embeddings")
+
+    # Load the embeddings from disk
+    new_embedder = CategoricalEmbedder(embedding_dim=3)
+    new_embedder.label_encoders = (
+        embedder.label_encoders
+    )  # Assuming label encodings are consistent across runs
+    new_embedder.load_embeddings("./embeddings")
+
+    # Transform the data using the loaded embeddings
+    processed_df_loaded = new_embedder.transform(df, categorical_cols=["color", "size"])
+    print("\nProcessed DataFrame with Loaded Embeddings:")
+    print(processed_df_loaded.head())
+
+    # Inverse transform the data
+    df_loaded = new_embedder.inverse_transform(
+        processed_df_loaded, categorical_cols=["color", "size"]
+    )
+    print("\nOriginal DataFrame:")
+    print(df.head())
+    print("\nProcessed DataFrame with Inverse Transform:")
+    print(df_loaded.head())

likelihood/tools/tools.py

@@ -8,10 +8,15 @@ import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 import yaml
+from packaging import version
 from pandas.core.frame import DataFrame
 
-# Suppress RankWarning
-warnings.simplefilter("ignore", np.RankWarning)
+if version.parse(np.__version__) < version.parse("2.0.0"):
+    filter = np.RankWarning
+else:
+    filter = np.exceptions.RankWarning
+
+warnings.simplefilter("ignore", filter)
 
 # -------------------------------------------------------------------------
 

{likelihood-1.5.7.dist-info → likelihood-2.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: likelihood
-Version: 1.5.7
+Version: 2.0.0
 Summary: A package that performs the maximum likelihood algorithm.
 Home-page: https://github.com/jzsmoreno/likelihood/
 Author: J. A. Moreno-Guerra
@@ -20,9 +20,10 @@ Requires-Dist: pydocstyle>=6.3.0
 Requires-Dist: flake8>=6.0.0
 Requires-Dist: isort>=5.12.0
 Requires-Dist: mypy>=1.4.1
-Requires-Dist: numpy<2.0.0
+Requires-Dist: numpy<3.0.0,>=1.26.4
 Requires-Dist: pydot==2.0.0
 Requires-Dist: matplotlib
+Requires-Dist: packaging
 Requires-Dist: graphviz
 Requires-Dist: seaborn
 Requires-Dist: pyyaml
@@ -32,7 +33,7 @@ Requires-Dist: tqdm
 Provides-Extra: full
 Requires-Dist: networkx; extra == "full"
 Requires-Dist: pyvis; extra == "full"
-Requires-Dist: tensorflow==2.15.0; extra == "full"
+Requires-Dist: tensorflow>=2.15.0; extra == "full"
 Requires-Dist: keras-tuner; extra == "full"
 Requires-Dist: scikit-learn; extra == "full"
 Dynamic: author

likelihood-2.0.0.dist-info/RECORD

@@ -0,0 +1,30 @@
+likelihood/__init__.py,sha256=5C0hapdsk85XZhN_rssRAEFpkRRuKNtj6cyRbqD2_gM,994
+likelihood/main.py,sha256=fcCkGOOWKjfvw2tLVqjuKPV8t0rVCIT9FlbYcOv4EYo,7974
+likelihood/graph/__init__.py,sha256=vUY4pKlnm3eSVTXd2d-5JDPawhqGNRIKRhaHIobsNws,188
+likelihood/graph/_nn.py,sha256=Sh7dRz8QSI08Ydfw9e--uCxc4KMtHUsCz_-C-loXklQ,13883
+likelihood/graph/graph.py,sha256=bLrNMvIh7GOTdPTwnNss8oPZ7cbSHQScAsH_ttmVUK0,3294
+likelihood/graph/nn.py,sha256=uxCxGt1suKmThmEjFope2ew93-WlgvGhgr6RVCHwzhM,11420
+likelihood/models/__init__.py,sha256=e6nB4w47w0Q9DrAFeP3OcUgcoHOtf7Il4mBhgf4AARg,52
+likelihood/models/hmm.py,sha256=0s0gFySH1u4NjRaZDxiZ8oeTaFhFrw1x0GJxwy3dFrA,6253
+likelihood/models/regression.py,sha256=9cakyGlJCEO6WfpoKLh3GxdXQeQp7cUvJIkQ5odT0TA,9404
+likelihood/models/simulation.py,sha256=xsl4mJ2qFCuZR_B9LfQcLjV6OtONU1zyESX3CCUfOiw,8619
+likelihood/models/utils.py,sha256=dvigPi_hxcs5ntfHr7Y1JvP5ULtMW3kkN0nJpS4orE8,1319
+likelihood/models/deep/__init__.py,sha256=I55FciI0BfljYdhW2OGNqcpYV57FhPZETZX7Y1y9GVQ,303
+likelihood/models/deep/_autoencoders.py,sha256=CeD79YzU7DdPd92wUNG_EtPVQOBgsgYoC4uS2JF3b6o,30939
+likelihood/models/deep/_predictor.py,sha256=XI4QfVM7PS_60zYtmi-V8UzNDrASFiDMVPmV17BB8lM,27984
+likelihood/models/deep/autoencoders.py,sha256=muUBH9BclOK8ViI7PijyMOBBLVox6uwuIabyJvpU5qw,30729
+likelihood/models/deep/gan.py,sha256=rTnaLmIPjsKg6_0B8JZOVwPxdx59rHmqvzDitdJMCQ4,10924
+likelihood/models/deep/predictor.py,sha256=q5tPaAbF7s5XIcxVr6fyHTQdZa9tlixO9vb9a9Cw0wM,27831
+likelihood/models/deep/rl.py,sha256=9dhhnVTIETi9zvVeyOXYo1hl-LQJezmv0rgsUq11Qwc,11611
+likelihood/tools/__init__.py,sha256=N1IhMDzacsGQT2MIYBMBC0zTxes78vC_0gGrwkuPgmg,78
+likelihood/tools/cat_embed.py,sha256=SJ7o1vbrNYp21fLLcjRnWpUDcz1nVSe8TmMvsLIz5CI,7346
+likelihood/tools/figures.py,sha256=waF0NHIMrctCmaLhcuz5DMcXyRKynmn6aG0XITYCTLc,10940
+likelihood/tools/impute.py,sha256=n87Tv-xLUAdPl7BQLFcLWSsXBZbXksahyCayJWMydXc,9485
+likelihood/tools/models_tools.py,sha256=c3-vac-1MYSarYDtfR6XfVC7X_WY9auS7y2_3Z973IQ,8875
+likelihood/tools/numeric_tools.py,sha256=Hwf-lbqROqPPZ9N7eVzKIDyZxFGQdP53isWxPqpG0eo,12254
+likelihood/tools/tools.py,sha256=GKZsqjyO5tGXWGSfn3jlQBTjRlmBv2byfvpu-QclUx0,42188
+likelihood-2.0.0.dist-info/licenses/LICENSE,sha256=XWHWt9egYEUHGPTnlcZfJKLPmysacOwdiLj_-J7Z9ew,1066
+likelihood-2.0.0.dist-info/METADATA,sha256=Ziysy1MQuW77OHHd1UzMtlfeUT9wsdgCl6rxW3uLBEE,2917
+likelihood-2.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+likelihood-2.0.0.dist-info/top_level.txt,sha256=KDiBLr870YTxqLFqObTOSrTK10uw8dFsITSNLlte3PA,11
+likelihood-2.0.0.dist-info/RECORD,,

likelihood-1.5.7.dist-info/RECORD

@@ -1,25 +0,0 @@
-likelihood/__init__.py,sha256=5C0hapdsk85XZhN_rssRAEFpkRRuKNtj6cyRbqD2_gM,994
-likelihood/main.py,sha256=fcCkGOOWKjfvw2tLVqjuKPV8t0rVCIT9FlbYcOv4EYo,7974
-likelihood/graph/__init__.py,sha256=6TuFDfmXTwpLyHl7_KqBfdzW6zqHjGzIFvymjFPlvjI,21
-likelihood/graph/graph.py,sha256=bLrNMvIh7GOTdPTwnNss8oPZ7cbSHQScAsH_ttmVUK0,3294
-likelihood/graph/nn.py,sha256=uxCxGt1suKmThmEjFope2ew93-WlgvGhgr6RVCHwzhM,11420
-likelihood/models/__init__.py,sha256=e6nB4w47w0Q9DrAFeP3OcUgcoHOtf7Il4mBhgf4AARg,52
-likelihood/models/hmm.py,sha256=0s0gFySH1u4NjRaZDxiZ8oeTaFhFrw1x0GJxwy3dFrA,6253
-likelihood/models/regression.py,sha256=9cakyGlJCEO6WfpoKLh3GxdXQeQp7cUvJIkQ5odT0TA,9404
-likelihood/models/simulation.py,sha256=6OD2IXAnbctxtOzUJ2b9vKW7_tdGs4dQYmQQShqsioA,8443
-likelihood/models/utils.py,sha256=dvigPi_hxcs5ntfHr7Y1JvP5ULtMW3kkN0nJpS4orE8,1319
-likelihood/models/deep/__init__.py,sha256=UV_VYhySvrNnB4a0VXYM4wK3KKF7ytjLFFfwvnaZWaA,82
-likelihood/models/deep/autoencoders.py,sha256=9-ZOKbS02tojCufg_Fbd5_Z48pSFSqZnfZZJVohNqdk,29985
-likelihood/models/deep/gan.py,sha256=aoSaNO5LvCU62cjxA0AxvnQvE7NSFtrp1Ta4EDJchpo,10874
-likelihood/models/deep/predictor.py,sha256=Z6GVm9ciz90cMcp4Q6Lvm-_8_9ZOxX1kBquReW2aGqM,27688
-likelihood/tools/__init__.py,sha256=N1IhMDzacsGQT2MIYBMBC0zTxes78vC_0gGrwkuPgmg,78
-likelihood/tools/figures.py,sha256=waF0NHIMrctCmaLhcuz5DMcXyRKynmn6aG0XITYCTLc,10940
-likelihood/tools/impute.py,sha256=n87Tv-xLUAdPl7BQLFcLWSsXBZbXksahyCayJWMydXc,9485
-likelihood/tools/models_tools.py,sha256=c3-vac-1MYSarYDtfR6XfVC7X_WY9auS7y2_3Z973IQ,8875
-likelihood/tools/numeric_tools.py,sha256=Hwf-lbqROqPPZ9N7eVzKIDyZxFGQdP53isWxPqpG0eo,12254
-likelihood/tools/tools.py,sha256=lk9BIskjUKYQ1XVwARm9jAjHuLQ4UO68aZY8oxkzk5c,42056
-likelihood-1.5.7.dist-info/licenses/LICENSE,sha256=XWHWt9egYEUHGPTnlcZfJKLPmysacOwdiLj_-J7Z9ew,1066
-likelihood-1.5.7.dist-info/METADATA,sha256=V8yQ5NJPbMyxOB7sICsp5QCkZ8MZhxkfS-4WCWMrFG0,2883
-likelihood-1.5.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-likelihood-1.5.7.dist-info/top_level.txt,sha256=KDiBLr870YTxqLFqObTOSrTK10uw8dFsITSNLlte3PA,11
-likelihood-1.5.7.dist-info/RECORD,,