upgini 1.2.46__py3-none-any.whl → 1.2.47__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.46"
+__version__ = "1.2.47"

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.dist-info → upgini-1.2.47.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.46
+Version: 1.2.47
 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-1.2.46.dist-info → upgini-1.2.47.dist-info}/RECORD

@@ -1,10 +1,10 @@
-upgini/__about__.py,sha256=s7kBVARFz8lSmh7ulygN5xbxPrps18XAib1Arlvg6cw,23
+upgini/__about__.py,sha256=o2NRe9gScRz1I1oB_R5MjkQ4w7BrDovQP2Z_Mq2c6bo,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=QC3jncWS3wHe4CY7pWWDMO_3HKxGbi0EyPHXMdBtoQM,33456
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=NWYNZtSgAR05zOZp_Wq1ltVGThCttTbVN_TP2RaWFSI,200008
-upgini/http.py,sha256=plZGTGoi1h2edd8Cnjt4eYB8t4NbBGnZz7DtPTByiNc,42885
+upgini/http.py,sha256=danPeX7nTMa_70S-pk-4UUm5yOvXYlR84jgyjoHYBkU,43367
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=-ibqiNjD7dTagqg53FoEJNEqvAYbwgfyn9PGTRQ_YKU,12054
 upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.46.dist-info/METADATA,sha256=79LcIjwGCdKUlidUqvLOy4YnlBIJEyJwLE5tAPxlKo8,49055
-upgini-1.2.46.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.46.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.46.dist-info/RECORD,,
+upgini-1.2.47.dist-info/METADATA,sha256=4pKaboM3TxupdS6iw1Uh_IW9Dw0X88LnDh1pGjsc3fs,49055
+upgini-1.2.47.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.47.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.47.dist-info/RECORD,,

{upgini-1.2.46.dist-info → upgini-1.2.47.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.24.2
+Generator: hatchling 1.25.0
 Root-Is-Purelib: true
 Tag: py3-none-any