upgini 1.1.312a3__tar.gz → 1.1.312a4__tar.gz

{upgini-1.1.312a3 → upgini-1.1.312a4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.312a3
+Version: 1.1.312a4
 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-1.1.312a4/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.312a4"

{upgini-1.1.312a3 → upgini-1.1.312a4}/src/upgini/dataset.py

@@ -440,9 +440,11 @@ class Dataset:  # (pd.DataFrame):
                 FileColumnMeaningType.DATETIME,
                 # FileColumnMeaningType.IP_ADDRESS,
             }:
+                min_value = self.data[column_name].astype("Int64").min()
+                max_value = self.data[column_name].astype("Int64").max()
                 min_max_values = NumericInterval(
-                    minValue=self.data[column_name].astype("Int64").min(),
-                    maxValue=self.data[column_name].astype("Int64").max(),
+                    minValue=min_value,
+                    maxValue=max_value,
                 )
             else:
                 min_max_values = None

{upgini-1.1.312a3 → upgini-1.1.312a4}/src/upgini/utils/datetime_utils.py

@@ -1,6 +1,7 @@
 import datetime
 import logging
 import re
+import pytz
 from typing import Dict, List, Optional
 
 import numpy as np
@@ -28,12 +29,13 @@ DATE_FORMATS = [
     "%Y-%m-%dT%H:%M:%S.%f",
 ]
 
-DATETIME_PATTERN = r"^[\d\s\.\-:T/]+$"
+DATETIME_PATTERN = r"^[\d\s\.\-:T/+]+$"
 
 
 class DateTimeSearchKeyConverter:
     DATETIME_COL = "_date_time"
-    MIN_SUPPORTED_DATE_TS = datetime.datetime(1999, 12, 31)  # 946684800000  # 2000-01-01
+    # MIN_SUPPORTED_DATE_TS = datetime.datetime(1999, 12, 31)  # 946684800000  # 2000-01-01
+    MIN_SUPPORTED_DATE_TS = pd.to_datetime(datetime.datetime(1999, 12, 31)).tz_localize(None)
 
     def __init__(
         self,
@@ -106,12 +108,13 @@ class DateTimeSearchKeyConverter:
             df[self.date_column] = df[self.date_column].astype("string").apply(self.clean_date)
             df[self.date_column] = self.parse_date(df)
 
-        df = self.clean_old_dates(df)
-
         # If column with date is datetime then extract seconds of the day and minute of the hour
         # as additional features
         seconds = "datetime_seconds"
         df[self.date_column] = df[self.date_column].dt.tz_localize(None)
+
+        df = self.clean_old_dates(df)
+
         df[seconds] = (df[self.date_column] - df[self.date_column].dt.floor("D")).dt.seconds
 
         seconds_without_na = df[seconds].dropna()

{upgini-1.1.312a3 → upgini-1.1.312a4}/src/upgini/utils/phone_utils.py

@@ -29,21 +29,21 @@ class PhoneSearchKeyConverter:
     def convert(self, df: pd.DataFrame) -> pd.DataFrame:
         df = self.phone_to_int(df)
         if self.country_column is not None:
-            df = df.apply(self.add_prefix, axis=1)
+            df[self.phone_column] = df.apply(self.add_prefix, axis=1)
         df[self.phone_column] = df[self.phone_column].astype("Int64")
         return df
 
     def add_prefix(self, row):
         phone = row[self.phone_column]
         if pd.isna(phone):
-            return row
+            return phone
         country = row[self.country_column]
         country_prefix_tuple = self.COUNTRIES_PREFIXES.get(country)
         if country_prefix_tuple is not None:
             country_prefix, number_of_digits = country_prefix_tuple
             if len(str(phone)) == number_of_digits:
-                row[self.phone_column] = int(country_prefix + str(phone))
-        return row
+                return int(country_prefix + str(phone))
+        return phone
 
     def phone_to_int(self, df: pd.DataFrame) -> pd.DataFrame:
         """

upgini-1.1.312a3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.312a3"