upgini 1.2.46__tar.gz → 1.2.48__tar.gz

{upgini-1.2.46 → upgini-1.2.48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.46
+Version: 1.2.48
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.2.48/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.48"

{upgini-1.2.46 → upgini-1.2.48}/src/upgini/features_enricher.py

@@ -1486,8 +1486,8 @@ class FeaturesEnricher(TransformerMixin):
             for c in X_sampled.columns.to_list()
             if (
                 not self.fit_select_features
-                or c in self.feature_names_
-                or (self.fit_columns_renaming is not None and self.fit_columns_renaming.get(c) in self.feature_names_)
+                or c in set(self.feature_names_).union(self.id_columns)
+                or (self.fit_columns_renaming or {}).get(c, c) in set(self.feature_names_).union(self.id_columns)
             )
             and c
             not in (
@@ -2191,7 +2191,9 @@ if response.status_code == 200:
 
             search_keys = self.search_keys.copy()
             if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
-                self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in self.id_columns})
+                self.search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in self.id_columns if col not in self.search_keys}
+                )
 
             search_keys = self.__prepare_search_keys(
                 validated_X, search_keys, is_demo_dataset, is_transform=True, silent_mode=silent_mode
@@ -2716,8 +2718,12 @@ if response.status_code == 200:
         if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
             id_columns = self.__get_renamed_id_columns()
             if id_columns:
-                self.fit_search_keys.update({col: SearchKey.CUSTOM_KEY for col in id_columns})
-                self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in self.id_columns})
+                self.fit_search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in id_columns if col not in self.fit_search_keys}
+                )
+                self.search_keys.update(
+                    {col: SearchKey.CUSTOM_KEY for col in self.id_columns if col not in self.search_keys}
+                )
                 self.runtime_parameters.properties["id_columns"] = ",".join(id_columns)
 
         df, fintech_warnings = remove_fintech_duplicates(

{upgini-1.2.46 → upgini-1.2.48}/src/upgini/http.py

@@ -16,7 +16,7 @@ from typing import Any, Dict, List, Optional, Tuple
 from urllib.parse import urljoin
 
 import jwt
-import pandas as pd
+# import pandas as pd
 import requests
 from pydantic import BaseModel
 from pythonjsonlogger import jsonlogger
@@ -422,6 +422,16 @@ class _RestClient:
                     lambda: self._send_post_file_req_v2(api_path, files, trace_id=trace_id, need_json_response=False)
                 )
 
+    @staticmethod
+    def compute_file_digest(filepath: str, algorithm="sha256", chunk_size=4096) -> str:
+        hash_func = getattr(hashlib, algorithm)()
+
+        with open(filepath, "rb") as f:
+            for chunk in iter(lambda: f.read(chunk_size), b""):
+                hash_func.update(chunk)
+
+        return hash_func.hexdigest()
+
     def initial_search_v2(
         self,
         trace_id: str,
@@ -442,9 +452,10 @@ class _RestClient:
                 digest = md5_hash.hexdigest()
                 metadata_with_md5 = metadata.copy(update={"checksumMD5": digest})
 
-            digest_sha256 = hashlib.sha256(
-                pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
-            ).hexdigest()
+            # digest_sha256 = hashlib.sha256(
+            #     pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
+            # ).hexdigest()
+            digest_sha256 = self.compute_file_digest(file_path)
             metadata_with_md5 = metadata_with_md5.copy(update={"digest": digest_sha256})
 
             with open(file_path, "rb") as file:
@@ -530,9 +541,10 @@ class _RestClient:
                 digest = md5_hash.hexdigest()
                 metadata_with_md5 = metadata.copy(update={"checksumMD5": digest})
 
-            digest_sha256 = hashlib.sha256(
-                pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
-            ).hexdigest()
+            # digest_sha256 = hashlib.sha256(
+            #     pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
+            # ).hexdigest()
+            digest_sha256 = self.compute_file_digest(file_path)
             metadata_with_md5 = metadata_with_md5.copy(update={"digest": digest_sha256})
 
             with open(file_path, "rb") as file:

upgini-1.2.46/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.46"