Merge pull request #1200 from mindsdb/staging

Release 23.12.4.0

Author: paxcema

.github/workflows/ligthtwood.yml

@@ -6,6 +6,8 @@ on:
     branches:
       - stable
       - staging
+  release:
+    types: [ published ]
 
 
 jobs:
@@ -46,7 +48,7 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     needs: test
-    if: github.ref == 'refs/heads/stable'
+    if: github.ref == 'refs/heads/stable' || github.event_name == 'release'
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python

MANIFEST.in

@@ -1 +1 @@
-include requirements.txt
+include requirements*.txt

docssrc/source/tutorials/tutorial_data_analysis/tutorial_data_analysis.ipynb

@@ -295,10 +295,10 @@
     }
    ],
    "source": [
-    "from type_infer.infer import infer_types\n",
+    "from type_infer.api import infer_types\n",
     "from type_infer.base import TypeInformation\n",
     "\n",
-    "type_information = infer_types(df, problem_definition.pct_invalid)\n",
+    "type_information = infer_types(df, config={'engine': 'rule_based', 'pct_invalid': problem_definition.pct_invalid})\n",
     "\n",
     "{field.name for field in fields(TypeInformation)}  # show the fields this dataclass has"
    ]

lightwood/__about__.py

@@ -1,6 +1,6 @@
 __title__ = 'lightwood'
 __package_name__ = 'lightwood'
-__version__ = '23.11.1.0'
+__version__ = '23.12.4.0'
 __description__ = "Lightwood is a toolkit for automatic machine learning model building"
 __email__ = "community@mindsdb.com"
 __author__ = 'MindsDB Inc'

lightwood/api/high_level.py

@@ -4,7 +4,7 @@
 import pandas as pd
 from lightwood.api.types import JsonAI, ProblemDefinition
 from dataprep_ml.insights import statistical_analysis
-from type_infer.infer import infer_types
+from type_infer.api import infer_types
 from lightwood.api.predictor import PredictorInterface
 from lightwood.api.json_ai import generate_json_ai
 from lightwood.helpers.codegen import code_from_json_ai as _code_from_json_ai, _module_from_code, _predictor_from_code
@@ -65,7 +65,7 @@ def json_ai_from_problem(df: pd.DataFrame, problem_definition: Union[ProblemDefi
         log.info(f'Dropping features: {problem_definition.ignore_features}')
         df = df.drop(columns=problem_definition.ignore_features)
 
-    type_information = infer_types(df, problem_definition.pct_invalid)
+    type_information = infer_types(df, config={'engine': 'rule_based', 'pct_invalid': problem_definition.pct_invalid})
     stats = statistical_analysis(
         df, type_information.dtypes, problem_definition.to_dict(), type_information.identifiers)
 

lightwood/encoder/text/short.py

@@ -2,7 +2,7 @@
 import torch
 from lightwood.encoder import BaseEncoder
 from lightwood.encoder.categorical import CategoricalAutoEncoder
-from type_infer.helpers import tokenize_text
+from type_infer.rule_based.helpers import tokenize_text
 from lightwood.helpers.torch import concat_vectors_and_pad, average_vectors
 import pandas as pd
 

tests/unit_tests/encoder/text/test_short.py

@@ -1,7 +1,7 @@
 import random
 import unittest
 from lightwood.encoder.text.short import ShortTextEncoder
-from type_infer.helpers import tokenize_text
+from type_infer.rule_based.helpers import tokenize_text
 import torch
 
 VOCAB = [