upgini 1.2.60a3792.dev2__py3-none-any.whl → 1.2.62a3818.dev1__py3-none-any.whl

upgini/utils/target_utils.py

@@ -1,4 +1,3 @@
-import itertools
 import logging
 from typing import Callable, List, Optional, Union
 
@@ -208,7 +207,7 @@ def balance_undersample_forced(
     id_columns: List[str],
     date_column: str,
     task_type: ModelTaskType,
-    cv_type: CVType | None,
+    cv_type: Optional[CVType],
     random_state: int,
     sample_size: int = 7000,
     logger: Optional[logging.Logger] = None,
@@ -372,7 +371,8 @@ def balance_undersample_time_series(
     if len(id_counts) < min_different_ids:
         if logger is not None:
             logger.info(
-                f"Different ids count {len(id_counts)} for sample size {sample_size} is less than min different ids {min_different_ids}, sampling time window"
+                f"Different ids count {len(id_counts)} for sample size {sample_size}"
+                f" is less than min different ids {min_different_ids}, sampling time window"
             )
         date_counts = df.groupby(id_columns)[date_column].nunique().sort_values(ascending=False)
         ids_to_sample = date_counts.index[:min_different_ids] if len(id_counts) > 0 else date_counts.index

upgini/utils/ts_utils.py

@@ -8,23 +8,17 @@ def get_most_frequent_time_unit(df: pd.DataFrame, id_columns: List[str], date_co
     def closest_unit(diff):
         return pd.tseries.frequencies.to_offset(pd.Timedelta(diff, unit="s"))
 
-    # Calculate differences for each ID group
     all_diffs = []
     groups = df.groupby(id_columns) if id_columns else [(None, df)]
     for _, group in groups:
-        # Get sorted dates for this group
         group_dates = group[date_column].sort_values().unique()
         if len(group_dates) > 1:
-            # Calculate time differences between consecutive dates
             diff_series = pd.Series(group_dates[1:] - group_dates[:-1])
-            # Convert to nanoseconds
             diff_ns = diff_series.dt.total_seconds()
             all_diffs.extend(diff_ns)
 
-    # Convert to series for easier processing
     all_diffs = pd.Series(all_diffs)
 
-    # Get most common time unit across all groups
     most_frequent_unit = all_diffs.apply(closest_unit).mode().min()
 
     return most_frequent_unit if isinstance(most_frequent_unit, pd.DateOffset) else None

{upgini-1.2.60a3792.dev2.dist-info → upgini-1.2.62a3818.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.60a3792.dev2
+Version: 1.2.62a3818.dev1
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -30,6 +30,7 @@ Requires-Dist: jarowinkler>=2.0.0
 Requires-Dist: levenshtein>=0.25.1
 Requires-Dist: numpy<=1.26.4,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
+Requires-Dist: psutil>=6.0.0
 Requires-Dist: pydantic<3.0.0,>1.0.0
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: python-bidi==0.4.2

{upgini-1.2.60a3792.dev2.dist-info → upgini-1.2.62a3818.dev1.dist-info}/RECORD

@@ -1,36 +1,37 @@
-upgini/__about__.py,sha256=8VHknGDFZaUmYuHXftocfi6wQkP1htM0HF9T5bSV43M,33
+upgini/__about__.py,sha256=-inFSOjK0otU7oAU9xIxafvjGaGWyHQqEAz5nWw5yqI,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=OGjpeFHbj3lWiZTOHTpWEoMMDmFY1FlNC44FKktoZvU,34956
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=IXU6ahvQqMGLdZsrHCjOGEia1pBAgixfld3pNVPcGEM,202468
+upgini/features_enricher.py,sha256=cB2I5rNpbztjkYEEW5aJuKj2fCMnfxp40X4Eo63oyuQ,205340
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
-upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
+upgini/metrics.py,sha256=t7uOOnlDYvP6E3DLjPMQcFBjyhJfUQY8aUlx7N0Mh-s,35477
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=v0_NozalvvzeojSAA0d7UJ5INS654ZVaLn4S8djK6Ac,329
-upgini/autofe/binary.py,sha256=zMhtHVuGUAFLUqem-XiXqJj-GRXxS88tdz8tFuDfSNM,7659
-upgini/autofe/date.py,sha256=oykxfmny4LOr6m79IipOUCtk2JQSUdSCWHh8K9n7nek,10726
-upgini/autofe/feature.py,sha256=zvRdlxCkaOsX0XiragNvh0tAPyOWut0MQTq5JGU5HtY,14749
-upgini/autofe/groupby.py,sha256=G48_sQZw016eGx3cOy8YQrEIOp95puWqYUpFWd-gdeM,3595
-upgini/autofe/operand.py,sha256=8Ttrfxv_H91dMbS7J55zxluzAJHfGXU_Y2xCh4OHwb8,4774
-upgini/autofe/unary.py,sha256=T3E7F3dA_7o_rkdCFq7JV6nHLzcoHLHQTcxO7y5Opa4,4646
-upgini/autofe/vector.py,sha256=udkg4pP7IIeLjt0Cg6rzEKUmGaubOnqsEz3bz9R6E44,7110
+upgini/autofe/all_operands.py,sha256=VIT5jCq5U-qypdNz1MIQ_hlIAs0ujJgRfKRUkU24nFs,332
+upgini/autofe/binary.py,sha256=jsXa_zwlNWRmQAT5qipzU2Or03qae-a1kkY9yDECkq8,7660
+upgini/autofe/date.py,sha256=bmoXU5vlDa1xsfCIFEC_VMRHOnV8Sy_KUMshqh0ARvA,10722
+upgini/autofe/feature.py,sha256=n4sNNFM9b022AGJbW14AMRuERD9bwub-RWqa6hfLID0,14750
+upgini/autofe/groupby.py,sha256=NN0T-tYbTHQDeCi2UZ06wVkDflm8DJBV4rdGrrVyVEE,3596
+upgini/autofe/operator.py,sha256=VCGDUQ5bOtwX-jzmgHDrKF3GbglDumyEkvtLWTmSGQo,4776
+upgini/autofe/timeseries.py,sha256=Pci7kNpFcViNZdIHlVTyxjoxzcMVdqUPopbPrJ3hE20,6593
+upgini/autofe/unary.py,sha256=my7AYIrWCQPFxRtcphONmwieU5HpX4fHiKllFRCsMUk,4647
+upgini/autofe/vector.py,sha256=5Lx2q_Np9PrMtZ_8O86xywq0s4XSQbooHxK3ufo3ANU,664
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=0vaYz5v3KclJnA6jAWiTUiMQO5mbBTBINWV9jr2F5xM,22591
+upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=UXMiaFP3p-WdiXyZJN3O_OZstb-F33BWVDxDiofyxd4,27464
+upgini/resource_bundle/strings.properties,sha256=3zctRNQDJ1STTvLUfryBT72wYeHYnrllV4rG1C3HtfI,27542
 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=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -43,7 +44,7 @@ upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl
 upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk,6937
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=RVAk4_rakK8X9zjybK3-rj0to0e3elye8tnBuA4wTWU,13491
+upgini/utils/datetime_utils.py,sha256=_jq-kn_dGNFfs-DGXcWCGzy9bkplfAjrZ8SsmN28zXc,13535
 upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
@@ -52,15 +53,17 @@ upgini/utils/feature_info.py,sha256=0rOXSyCj-sw-8migWP0ge8qrOzGU50dQvH0JUJUrDfQ,
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=TSQ_qDsLlVnm09X1HacpabEf_HNqSWpxBF4Sdc2xs08,6580
+upgini/utils/mstats.py,sha256=GjBAUacgfAoVQVFUrMiRYdVkmx93CIThLRNvYLLiV48,5765
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
-upgini/utils/target_utils.py,sha256=gGIO40NmLdm1DWaZNPWPoCIPlLNIDZWFGjoPuhOlzAU,16573
+upgini/utils/sort.py,sha256=w-CoT33W_53ekOROpKI_VRsRmiyWNr2b3IpE5_4MLLA,6395
+upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,16579
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
-upgini/utils/ts_utils.py,sha256=_YbNVE144vtEPlvLpvPGguDNzrnUM9IIjdX2VQz4T7E,1671
+upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.60a3792.dev2.dist-info/METADATA,sha256=9ViiZMTzdvTgcXn1tdN-TUgwOW7ovx7JoOQk_VZfMf0,49065
-upgini-1.2.60a3792.dev2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.60a3792.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.60a3792.dev2.dist-info/RECORD,,
+upgini-1.2.62a3818.dev1.dist-info/METADATA,sha256=9mRM2yQ18CeOTHQ83UgVmItZ-npsZSla3illeXSpyTQ,49094
+upgini-1.2.62a3818.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.62a3818.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.62a3818.dev1.dist-info/RECORD,,