upgini 1.1.264a1__py3-none-any.whl → 1.1.265__py3-none-any.whl

upgini/features_enricher.py

@@ -70,6 +70,7 @@ from upgini.utils.datetime_utils import (
     DateTimeSearchKeyConverter,
     is_blocked_time_series,
     is_time_series,
+    validate_dates_distribution,
 )
 from upgini.utils.deduplicate_utils import (
     clean_full_duplicates,
@@ -1922,7 +1923,7 @@ class FeaturesEnricher(TransformerMixin):
 
             meaning_types = {col: key.value for col, key in search_keys.items()}
             non_keys_columns = [column for column in df.columns if column not in search_keys.keys()]
-            # Don't pass 
+
             if email_converted_to_hem:
                 non_keys_columns.append(email_column)
 
@@ -2221,6 +2222,10 @@ class FeaturesEnricher(TransformerMixin):
         self.fit_search_keys = self.search_keys.copy()
         self.fit_search_keys = self.__prepare_search_keys(validated_X, self.fit_search_keys, is_demo_dataset)
 
+        validate_dates_distribution(
+            validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter
+        )
+
         has_date = self._get_date_column(self.fit_search_keys) is not None
         model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
         self._validate_binary_observations(validated_y, model_task_type)

upgini/resource_bundle/strings.properties

@@ -111,6 +111,7 @@ x_is_empty=X is empty
 y_is_empty=y is empty
 x_contains_reserved_column_name=Column name {} is reserved. Please rename column and try again
 missing_generate_feature=\nWARNING: Feature {} specified in `generate_features` is not present in input columns: {}
+x_unstable_by_date=\nWARNING: Your training sample is unstable in number of rows per date. It is recommended to redesign the training sample.
     # eval set validation
 unsupported_type_eval_set=Unsupported type of eval_set: {}. It should be list of tuples with two elements: X and y
 eval_set_invalid_tuple_size=eval_set contains a tuple of size {}. It should contain only pairs of X and y

upgini/utils/datetime_utils.py

@@ -1,7 +1,7 @@
 import datetime
 import logging
 import re
-from typing import List, Optional
+from typing import Dict, List, Optional
 
 import numpy as np
 import pandas as pd
@@ -9,7 +9,9 @@ from dateutil.relativedelta import relativedelta
 from pandas.api.types import is_numeric_dtype, is_period_dtype, is_string_dtype
 
 from upgini.errors import ValidationError
+from upgini.metadata import SearchKey
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
+from upgini.utils.warning_counter import WarningCounter
 
 DATE_FORMATS = [
     "%Y-%m-%d",
@@ -225,3 +227,49 @@ def is_blocked_time_series(df: pd.DataFrame, date_col: str, search_keys: List[st
 
     is_diff_less_than_two_columns = grouped.apply(check_differences)
     return is_diff_less_than_two_columns.all()
+
+
+def validate_dates_distribution(
+    X: pd.DataFrame,
+    search_keys: Dict[str, SearchKey],
+    logger: Optional[logging.Logger] = None,
+    bundle: Optional[ResourceBundle] = None,
+    warning_counter: Optional[WarningCounter] = None,
+):
+    maybe_date_col = None
+    for key, key_type in search_keys.items():
+        if key_type in [SearchKey.DATE, SearchKey.DATETIME]:
+            maybe_date_col = key
+
+    if maybe_date_col is None:
+        for col in X.columns:
+            if col in search_keys:
+                continue
+            try:
+                pd.to_datetime(X[col])
+                maybe_date_col = col
+                break
+            except Exception:
+                pass
+
+    if maybe_date_col is None:
+        return
+
+    dates = pd.to_datetime(X[maybe_date_col]).dt.date
+
+    date_counts = dates.value_counts().sort_index()
+
+    date_counts_1 = date_counts[: round(len(date_counts) / 2)]
+    date_counts_2 = date_counts[round(len(date_counts) / 2) :]
+    ratio = date_counts_2.mean() / date_counts_1.mean()
+
+    if ratio > 1.2 or ratio < 0.8:
+        if warning_counter is not None:
+            warning_counter.increment()
+        if logger is None:
+            logger = logging.getLogger("muted_logger")
+            logger.setLevel("FATAL")
+        bundle = bundle or get_custom_bundle()
+        msg = bundle.get("x_unstable_by_date")
+        print(msg)
+        logger.warning(msg)

upgini/utils/target_utils.py

@@ -132,9 +132,7 @@ def balance_undersample(
                 class_value = classes[class_idx]
                 class_count = vc[class_value]
                 sample_strategy[class_value] = min(class_count, quantile25_class_cnt * multiclass_bootstrap_loops)
-            sampler = RandomUnderSampler(
-                sampling_strategy=sample_strategy, random_state=random_state
-            )
+            sampler = RandomUnderSampler(sampling_strategy=sample_strategy, random_state=random_state)
             X = df[SYSTEM_RECORD_ID]
             X = X.to_frame(SYSTEM_RECORD_ID)
             new_x, _ = sampler.fit_resample(X, target)  # type: ignore
@@ -153,9 +151,7 @@ def balance_undersample(
         minority_class = df[df[target_column] == min_class_value]
         majority_class = df[df[target_column] != min_class_value]
         sample_size = min(len(majority_class), min_sample_threshold - min_class_count)
-        sampled_majority_class = majority_class.sample(
-            n=sample_size, random_state=random_state
-        )
+        sampled_majority_class = majority_class.sample(n=sample_size, random_state=random_state)
         resampled_data = df[
             (df[SYSTEM_RECORD_ID].isin(minority_class[SYSTEM_RECORD_ID]))
             | (df[SYSTEM_RECORD_ID].isin(sampled_majority_class[SYSTEM_RECORD_ID]))

{upgini-1.1.264a1.dist-info → upgini-1.1.265.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.264a1
+Version: 1.1.265
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.264a1.dist-info → upgini-1.1.265.dist-info}/RECORD

@@ -2,7 +2,7 @@ upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
 upgini/dataset.py,sha256=xb4gIANyGbdcuM8Awyq2pJPiH_3k_LEbETApJgAoRBA,45529
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=-RtPvppDLzAVXqak2FHBJQdvzPhk1EHskM__vcZoGEE,172730
+upgini/features_enricher.py,sha256=5rc9vcsCBwmRDb8aAPOFGmkRbC7_zGJGPlaSvkytqCk,172880
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
@@ -29,7 +29,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/phone_normalizer.py,sha256=lhwsPEnfyjeIsndW2EcQGZksXYsfxaQ1ghAzVYoDRKM,9927
 upgini/resource_bundle/__init__.py,sha256=hdvbqL0b0xMWbY6-kiYGsW1ro2GMiWpxxsO9uCv-h9Q,8379
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=AgAzMSq-_vt_uIALOlB_xPVfcQuYYWxGvrOm8lN1CkY,25522
+upgini/resource_bundle/strings.properties,sha256=_bEfgRl2a9sgoy2RxvIf26NemnCW5CM-1AWWpljwZQE,25664
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=CC-DvPbrN7zp5--SVFuUqkVmdWM_5F7R0Do98ETV82U,6421
@@ -41,7 +41,7 @@ upgini/utils/blocked_time_series.py,sha256=dMz5ewk3PsoeOrc3lDzInCVPS9u_2XQkV0W6P
 upgini/utils/country_utils.py,sha256=1KXhLSNqkNYVL3on8-zK0Arc_SspUH7AMZvGZICysOU,6462
 upgini/utils/custom_loss_utils.py,sha256=DBslpjWGPt7xTeypt78baR59012SYphbPsO_YLKdilo,3972
 upgini/utils/cv_utils.py,sha256=Tn01RJvpZGZh0PUQUimlBkV-AXwe7s6yjCNFtw352Uc,3525
-upgini/utils/datetime_utils.py,sha256=ol5Bgh98wU6KBY9z4QskNO0ja-L7HJL70HmTAjl7iRU,8836
+upgini/utils/datetime_utils.py,sha256=4ii5WphAHlb_NRmdJx35VZpTarJbAr-AnDw3XSzUSow,10346
 upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
 upgini/utils/display_utils.py,sha256=LKoSwjrE0xgS5_cqVhc2og2CQ1UCZ1nTI2VKboIhoQA,10858
 upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
@@ -53,11 +53,11 @@ upgini/utils/phone_utils.py,sha256=JNSkF8G6mgsN8Czy11pamaJdsY6rBINEMpi7jbVt_RA,4
 upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3x_zs,409
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
 upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,44027
-upgini/utils/target_utils.py,sha256=WVhhxpQVvnhsDV7ctlds51VFg7hz59S_MFUSoRZFszw,7204
+upgini/utils/target_utils.py,sha256=5BHcOsBRb4z7P8t3e9rsdXUWUUI7DBmQMmv-x6RwzHM,7152
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.264a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.264a1.dist-info/METADATA,sha256=2t2VzbA1zrEr428Dxp5FqaiSL1zthQIERsEwljj46eA,48158
-upgini-1.1.264a1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.264a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.264a1.dist-info/RECORD,,
+upgini-1.1.265.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.265.dist-info/METADATA,sha256=HX-CwFFNgXRRuZ00TELhLI1-3ufrny1K0uZc9p0JWdA,48156
+upgini-1.1.265.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.265.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.265.dist-info/RECORD,,