upgini 1.2.70a3832.dev3__py3-none-any.whl → 1.2.71a3832.dev3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of upgini might be problematic. Click here for more details.

upgini/metadata.py CHANGED
@@ -325,6 +325,10 @@ class RuntimeParameters(BaseModel):
325
325
  properties: Dict[str, Any] = {}
326
326
 
327
327
 
328
+ class AutoFEParameters(BaseModel):
329
+ ts_gap_days: Optional[int] = None
330
+
331
+
328
332
  class SearchCustomization(BaseModel):
329
333
  featuresFilter: Optional[FeaturesFilter] = None
330
334
  extractFeatures: Optional[bool] = None
@@ -137,6 +137,7 @@ x_and_eval_x_diff_types=X and eval_set X has different types: {} and {}
137
137
  baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input dataframe
138
138
  baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
139
139
  missing_features_for_transform=Missing some features for transform that were presented on fit: {}
140
+ missing_target_for_transform=Search contains features on target. Please add y to the call and try again
140
141
  missing_id_column=Id column {} not found in X
141
142
  # target validation
142
143
  empty_target=Target is empty in all rows
upgini/search_task.py CHANGED
@@ -168,7 +168,13 @@ class SearchTask:
168
168
  for meta in self.provider_metadata_v2:
169
169
  if meta.features_used_for_embeddings is not None:
170
170
  features_for_transform.update(meta.features_used_for_embeddings)
171
-
171
+ if meta.generated_features:
172
+ features_for_transform.update(
173
+ c.original_name
174
+ for f in meta.generated_features
175
+ for c in f.base_columns
176
+ if c.ads_definition_id is None
177
+ )
172
178
  return list(features_for_transform)
173
179
 
174
180
  def get_shuffle_kfold(self) -> Optional[bool]:
upgini/utils/mstats.py CHANGED
@@ -118,7 +118,7 @@ def spearmanr(
118
118
  # - dof: degrees of freedom
119
119
  # - t_stat: t-statistic
120
120
  # - alternative: 'two-sided', 'greater', 'less'
121
- def compute_t_pvalue(t_stat, dof, alternative='two-sided'):
121
+ def compute_t_pvalue(t_stat, dof, alternative="two-sided"):
122
122
  from scipy.stats import t
123
123
 
124
124
  if alternative == "two-sided":
upgini/utils/sort.py CHANGED
@@ -87,7 +87,7 @@ def get_sort_columns_dict(
87
87
  df_with_target = df_with_target.loc[~target.isna()]
88
88
  df = df_with_target.iloc[:, :-1]
89
89
  target = df_with_target.iloc[:, -1]
90
- df = df.fillna(df.mean())
90
+ df = df.fillna(df.apply(lambda x: int(x.mean()) if pd.api.types.is_integer_dtype(x) else x.mean()))
91
91
  omit_nan = False
92
92
  hashes = [hash_series(df[col]) for col in columns_for_sort]
93
93
  df = np.asarray(df, dtype=np.float32)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.3
2
2
  Name: upgini
3
- Version: 1.2.70a3832.dev3
3
+ Version: 1.2.71a3832.dev3
4
4
  Summary: Intelligent data search & enrichment for Machine Learning
5
5
  Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
6
6
  Project-URL: Homepage, https://upgini.com/
@@ -17,12 +17,11 @@ Classifier: Intended Audience :: Science/Research
17
17
  Classifier: Intended Audience :: Telecommunications Industry
18
18
  Classifier: License :: OSI Approved :: BSD License
19
19
  Classifier: Operating System :: OS Independent
20
- Classifier: Programming Language :: Python :: 3.8
21
- Classifier: Programming Language :: Python :: 3.9
22
20
  Classifier: Programming Language :: Python :: 3.10
21
+ Classifier: Programming Language :: Python :: 3.11
23
22
  Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
24
23
  Classifier: Topic :: Scientific/Engineering :: Information Analysis
25
- Requires-Python: <3.12,>=3.8
24
+ Requires-Python: <3.12,>=3.10
26
25
  Requires-Dist: fastparquet>=0.8.1
27
26
  Requires-Dist: ipywidgets>=8.1.0
28
27
  Requires-Dist: jarowinkler>=2.0.0
@@ -1,14 +1,14 @@
1
- upgini/__about__.py,sha256=uuivsPy9A1ISVUFLN2as6edeg8kbhfwpyVZyOBxEKu0,33
1
+ upgini/__about__.py,sha256=WFpSmDQJDJ12kIDBE_r-3PSrbqGx13uL2B8Ywy19f6Y,33
2
2
  upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
3
3
  upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
4
- upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
4
+ upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
5
5
  upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
6
- upgini/features_enricher.py,sha256=4IstUZpQu4gN322LtVvpDMzTiMe5vmtjDr-U17588kk,205808
6
+ upgini/features_enricher.py,sha256=Z6RSjqcqneGwWflsq1Q5rjf83awPNYqKpAgHRh7jils,204680
7
7
  upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
8
8
  upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
9
- upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
9
+ upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
10
10
  upgini/metrics.py,sha256=I0sVJLNp4fiIq7ZFcUdNTxJjFkzStdFuKbnf2niEGjc,38207
11
- upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
11
+ upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
12
12
  upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
13
13
  upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
14
14
  upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
@@ -16,19 +16,20 @@ upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo
16
16
  upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
17
17
  upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
18
18
  upgini/autofe/binary.py,sha256=MnQuFiERpocjCPQUjOljlsq5FE-04GPfwtNjzvfNMyU,7671
19
- upgini/autofe/date.py,sha256=I07psJerrxOcHao91PdSCk9X6KWu61IBVyFRLjGNgK8,10730
20
- upgini/autofe/feature.py,sha256=xgu6bVIlUJ5PCUgoXQRNcGkcMOhj-_BdDRmkB_qRFS4,14766
19
+ upgini/autofe/date.py,sha256=C86F7sPiscUGq2a45UtQA9ADWBWg0kt54mePHHzjbLE,10633
20
+ upgini/autofe/feature.py,sha256=y1x3wijhTVBmloayQAHiscqKU9Ll8kLcGm1PdvS357I,14910
21
21
  upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
22
22
  upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
23
23
  upgini/autofe/unary.py,sha256=yVgPvtfnPSOhrii0YgezddmgWPwyOBCR0JutaIkdTTc,4658
24
+ upgini/autofe/utils.py,sha256=fK1am2_tQj3fL2vDslblye8lmyfWgGIUOX1beYVBz4k,2420
24
25
  upgini/autofe/vector.py,sha256=l0KdKg-txlZxDSE4hPPfCtfGQofYbl7oaABPr830sPI,667
25
26
  upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
26
- upgini/autofe/timeseries/base.py,sha256=T9Ec8LKJbiwTUGGsd_xhM0U0NUJblqmKchkzUI1sK88,3755
27
- upgini/autofe/timeseries/cross.py,sha256=Sh5hAXZFWKaFRqf_JGODu9pWO2tmuV5VKyK9eX3i7-I,4931
27
+ upgini/autofe/timeseries/base.py,sha256=rWJqRuFAzTZEsUdWG5s1Vhif9zzRRmalASXvarufRxI,3610
28
+ upgini/autofe/timeseries/cross.py,sha256=BTINVwuZSbm_4NKkVm0FGM68SrvZLENZKXN7-UyvhYI,5319
28
29
  upgini/autofe/timeseries/delta.py,sha256=h0YhmI1TlPJnjwFpN_GQxLb6r59DQuucnG5tQAXSgjU,3520
29
30
  upgini/autofe/timeseries/lag.py,sha256=LfQtg484vuqM0mgY4Wft1swHX_Srq7OKKgZswCXoiXI,1882
30
- upgini/autofe/timeseries/roll.py,sha256=bNFMDszSYTWvB7EyhHbRY1DJqzSURvHlPAcBebt0y0Y,2878
31
- upgini/autofe/timeseries/trend.py,sha256=9p2Q5ByAi6cx9RH9teBTe8FyjSzqthznC2Lo5dsJ0ho,2051
31
+ upgini/autofe/timeseries/roll.py,sha256=zADKXU-eYWQnQ5R3am1yEal8uU6Tm0jLAixwPb_aCHg,2794
32
+ upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9er1k4,2129
32
33
  upgini/autofe/timeseries/volatility.py,sha256=9shUmIKjpWTHVYjj80YBsk0XheBJ9uBuLv5NW9Mchnk,7953
33
34
  upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
34
35
  upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
@@ -38,7 +39,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
38
39
  upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
39
40
  upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
40
41
  upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
41
- upgini/resource_bundle/strings.properties,sha256=XU5ulr5ZDQfGbFk9QdFDzl3oDMaw0eDYCPoEq3ZvIkw,27687
42
+ upgini/resource_bundle/strings.properties,sha256=mwQrerdJj3adzT-fHqvs6Qjf-rqDccsUzELDIXJKAmY,27791
42
43
  upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
43
44
  upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
44
45
  upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -60,17 +61,17 @@ upgini/utils/feature_info.py,sha256=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,
60
61
  upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
61
62
  upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
62
63
  upgini/utils/ip_utils.py,sha256=TSQ_qDsLlVnm09X1HacpabEf_HNqSWpxBF4Sdc2xs08,6580
63
- upgini/utils/mstats.py,sha256=dLJQr5Ak5BAoV-pDPpnfvMURZVkZ3_v250QzAsSlqY4,6286
64
+ upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
64
65
  upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
65
66
  upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
66
67
  upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
67
68
  upgini/utils/sklearn_ext.py,sha256=E7zfYqBW597LetYXHxyM-i4f8luHsGIuP6mMJ2wtSMs,44661
68
- upgini/utils/sort.py,sha256=H79A17NMoHtLbqLCPFx_MBUloLZcDKjOba_H4gCE3t8,6965
69
+ upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
69
70
  upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,16579
70
71
  upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
71
72
  upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
72
73
  upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
73
- upgini-1.2.70a3832.dev3.dist-info/METADATA,sha256=_eHvyDouLdNk5oiA0DK2HBPVmOqgjwy0Ud76LDaElGU,49149
74
- upgini-1.2.70a3832.dev3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
75
- upgini-1.2.70a3832.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
76
- upgini-1.2.70a3832.dev3.dist-info/RECORD,,
74
+ upgini-1.2.71a3832.dev3.dist-info/METADATA,sha256=BivEcgWfrBd-9ABlKcTJnAF4BuX6YBlWjOB0i0wBF4E,49101
75
+ upgini-1.2.71a3832.dev3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
76
+ upgini-1.2.71a3832.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
77
+ upgini-1.2.71a3832.dev3.dist-info/RECORD,,