linkml-store 0.1.13__py3-none-any.whl → 0.2.0__py3-none-any.whl

linkml_store/utils/stats_utils.py

@@ -0,0 +1,53 @@
+import numpy as np
+import pandas as pd
+
+
+def predictive_power(df, target_col, feature_cols, cv=5):
+    from sklearn.model_selection import cross_val_score
+    from sklearn.preprocessing import LabelEncoder
+    from sklearn.tree import DecisionTreeClassifier
+
+    # Prepare the data
+    X = df[feature_cols].copy()  # Create an explicit copy
+    y = df[target_col].copy()
+
+    # Encode categorical variables
+    for col in X.columns:
+        if X[col].dtype == "object":
+            X[col] = LabelEncoder().fit_transform(X[col].astype(str))
+
+    if y.dtype == "object":
+        y = LabelEncoder().fit_transform(y.astype(str))
+
+    # Adjust cv based on the number of unique values in y
+    n_unique = len(np.unique(y))
+    cv = min(cv, n_unique)
+
+    # Train a decision tree and get cross-validated accuracy
+    clf = DecisionTreeClassifier(random_state=42)
+
+    if cv < 2:
+        # If cv is less than 2, we can't do cross-validation, so we'll just fit and score
+        clf.fit(X, y)
+        return clf.score(X, y)
+    else:
+        scores = cross_val_score(clf, X, y, cv=cv)
+        return scores.mean()
+
+
+def analyze_predictive_power(df, columns=None, cv=5):
+    if columns is None:
+        columns = df.columns
+    results = pd.DataFrame(index=columns, columns=["predictive_power", "features"])
+
+    for target_col in columns:
+        feature_cols = [col for col in columns if col != target_col]
+        try:
+            power = predictive_power(df, target_col, feature_cols, cv)
+            results.loc[target_col, "predictive_power"] = power
+            results.loc[target_col, "features"] = ", ".join(feature_cols)
+        except Exception as e:
+            print(f"Error processing {target_col}: {str(e)}")
+            results.loc[target_col, "predictive_power"] = np.nan
+
+    return results

{linkml_store-0.1.13.dist-info → linkml_store-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linkml-store
-Version: 0.1.13
+Version: 0.2.0
 Summary: linkml-store
 License: MIT
 Author: Author 1
@@ -24,6 +24,7 @@ Provides-Extra: mongodb
 Provides-Extra: neo4j
 Provides-Extra: pyarrow
 Provides-Extra: renderer
+Provides-Extra: scipy
 Provides-Extra: tests
 Provides-Extra: validation
 Requires-Dist: black (>=24.0.0) ; extra == "tests"
@@ -51,9 +52,12 @@ Requires-Dist: pyarrow ; extra == "pyarrow"
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pymongo ; extra == "mongodb"
 Requires-Dist: pystow (>=0.5.4,<0.6.0)
+Requires-Dist: scikit-learn ; extra == "scipy"
+Requires-Dist: scipy ; extra == "scipy"
 Requires-Dist: seaborn ; extra == "analytics"
 Requires-Dist: sqlalchemy
 Requires-Dist: streamlit (>=1.32.2,<2.0.0) ; extra == "app"
+Requires-Dist: tiktoken ; extra == "llm"
 Requires-Dist: uvicorn ; extra == "fastapi"
 Description-Content-Type: text/markdown
 
@@ -61,11 +65,13 @@ Description-Content-Type: text/markdown
 
 An AI-ready data management and integration platform. LinkML-Store
 provides an abstraction layer over multiple different backends
-(including DuckDB, MongoDB, and local filesystems), allowing for
+(including DuckDB, MongoDB, Neo4j, and local filesystems), allowing for
 common query, index, and storage operations.
 
 For full documentation, see [https://linkml.io/linkml-store/](https://linkml.io/linkml-store/)
 
+See [these slides](https://docs.google.com/presentation/d/e/2PACX-1vSgtWUNUW0qNO_ZhMAGQ6fYhlXZJjBNMYT0OiZz8DDx8oj7iG9KofRs6SeaMXBBOICGknoyMG2zaHnm/embed?start=false&loop=false&delayms=3000) for a high level overview.
+
 __Warning__ LinkML-Store is still undergoing changes and refactoring,
 APIs and command line options are subject to change!
 
@@ -99,6 +105,23 @@ linkml-store -d duckdb:///db/my.db -c persons validate
 * API
 * Streamlit applications
 
+## The CRUDSI pattern
+
+Most database APIs implement the **CRUD** pattern: Create, Read, Update, Delete.
+LinkML-Store adds **Search** and **Inference** to this pattern, making it **CRUDSI**.
+
+The notion of "Search" and "Inference" is intended to be flexible and extensible,
+including:
+
+* Search
+   * Traditional keyword search
+   * Search using LLM Vector embeddings (*without* a dedicated vector database)
+   * Pluggable specialized search, e.g. genomic sequence (not yet implemented)
+* Inference (encompassing  *validation*, *repair*, and inference of missing data)
+   * Classic rule-based inference
+   * Inference using LLM Retrieval Augmented Generation (RAG)
+   * Statistical/ML inference
+
 ## Features
 
 ### Multiple Adapters
@@ -108,6 +131,8 @@ LinkML-Store is designed to work with multiple backends, giving a common abstrac
 * [MongoDB](https://linkml.io/linkml-store/how-to/Use-MongoDB.html)
 * [DuckDB](https://linkml.io/linkml-store/tutorials/Python-Tutorial.html)
 * [Solr](https://linkml.io/linkml-store/how-to/Query-Solr-using-CLI.html)
+* [Neo4j](https://linkml.io/linkml-store/how-to/Use-Neo4j.html)
+
 * Filesystem
 
 Coming soon: any RDBMS, any triplestore, Neo4J, HDF5-based stores, ChromaDB/Vector dbs ...
@@ -173,3 +198,4 @@ make app
 
 See [these slides](https://docs.google.com/presentation/d/e/2PACX-1vSgtWUNUW0qNO_ZhMAGQ6fYhlXZJjBNMYT0OiZz8DDx8oj7iG9KofRs6SeaMXBBOICGknoyMG2zaHnm/embed?start=false&loop=false&delayms=3000) for more details
 
+

{linkml_store-0.1.13.dist-info → linkml_store-0.2.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
 linkml_store/__init__.py,sha256=jlU6WOUAn8cKIhzbTULmBTWpW9gZdEt7q_RI6KZN1bY,118
 linkml_store/api/__init__.py,sha256=3CelcFEFz0y3MkQAzhQ9JxHIt1zFk6nYZxSmYTo8YZE,226
-linkml_store/api/client.py,sha256=aiWhLSAY0Wj7EfoXdEXMtGId1LSbvGya8dGEKdOB0iI,10989
-linkml_store/api/collection.py,sha256=Qi89f-iUSC1zKUgqSMuooklteO0wbJfYbeVkpn8CbIM,36186
-linkml_store/api/config.py,sha256=E-ma5hXQrs5Gyet2BB6CFJyPqNjXwAr1pr9H7AT2vOc,5159
-linkml_store/api/database.py,sha256=W5PzpIua8w6eCUqugGqOV6Y7O15g5FSZzzaQKDOfqak,28297
+linkml_store/api/client.py,sha256=3klBXenQVbLjNQF3WmYfjASt3zvKOfWaCNp5aJM81Ec,12034
+linkml_store/api/collection.py,sha256=7JndC6A9r3OVbR9aB6d_bdaYN53XU4FpppUterygOaE,37800
+linkml_store/api/config.py,sha256=71pxQ5jM-ETxJWU7CzmKjsH6IEJUMP5sml381u9TYVk,5654
+linkml_store/api/database.py,sha256=QVvUuLQPCxB4cvsS7rXqPSfoHkhcMzP9vUcsjkuEYds,29051
 linkml_store/api/queries.py,sha256=w0qnNeCH6pC9WTGoEQYd300MF6o0G3atz2YxN3WecAs,2028
 linkml_store/api/stores/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/api/stores/chromadb/__init__.py,sha256=e9BkOPuPnVQKA5PRKDulag59yGNHDP3U2_DnPSrFAKM,132
 linkml_store/api/stores/chromadb/chromadb_collection.py,sha256=RQUZx5oeotkzNihg-dlSevkiTiKY1d9x0bS63HF80W4,4270
 linkml_store/api/stores/chromadb/chromadb_database.py,sha256=dZA3LQE8-ZMhJQOzsUFyxehnKpFF7adR182aggfkaFY,3205
 linkml_store/api/stores/duckdb/__init__.py,sha256=rbQSDgNg-fdvi6-pHGYkJTST4p1qXUZBf9sFSsO3KPk,387
-linkml_store/api/stores/duckdb/duckdb_collection.py,sha256=d9aYNFt9t8itNmhb6H2PdsxHL1dkYiW0N9wF8SATk1g,6767
+linkml_store/api/stores/duckdb/duckdb_collection.py,sha256=yXnJpEiGK4lMyNuJykuvlKOqaV9ntqv0m0NZMOw0auk,6911
 linkml_store/api/stores/duckdb/duckdb_database.py,sha256=GH9bcOfHpNp6r-Eu1C3W0xuYcLsqGFDH1Sh4weifGaQ,9923
 linkml_store/api/stores/duckdb/mappings.py,sha256=tDce3W1Apwammhf4LS6cRJ0m4NiJ0eB7vOI_4U5ETY8,148
 linkml_store/api/stores/filesystem/__init__.py,sha256=KjvCjdttwqMHNeGyL-gr59zRz0--HFEWWUNNCJ5hITs,347
@@ -20,7 +20,7 @@ linkml_store/api/stores/hdf5/__init__.py,sha256=l4cIh3v7P0nPbwGIsfuCMD_serQ8q8c7
 linkml_store/api/stores/hdf5/hdf5_collection.py,sha256=mnpLMYehn3PuaIjp2dXrIWu8jh-bdQ84X2Ku83jMdEY,3805
 linkml_store/api/stores/hdf5/hdf5_database.py,sha256=EZbjrpaqiNDEFvoD5dZNcGBXA8z6HRNL81emueTZWNw,2714
 linkml_store/api/stores/mongodb/__init__.py,sha256=OSFCr7RQlDEe-O-Y0P_i912oAMK-L3pC7Cnj7sxlwAk,510
-linkml_store/api/stores/mongodb/mongodb_collection.py,sha256=W-j1tkk8h1-zzjIRe-IYAnAOwlFSwr4fnDtgiu7RsVI,6695
+linkml_store/api/stores/mongodb/mongodb_collection.py,sha256=unN0v7RYlGIiJxEhbNRxZ86TVQ4ELlAsNWTwEbg7E_g,6831
 linkml_store/api/stores/mongodb/mongodb_database.py,sha256=Y9MIV0KSRGCyopz8vGEivhSuvF0vZLCDJd29cdqMIX8,3857
 linkml_store/api/stores/neo4j/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/api/stores/neo4j/neo4j_collection.py,sha256=a-Az5_ypdBMgeNyhrTW7q-ik-vYPCDDONIK7N_CDA9c,17449
@@ -30,7 +30,7 @@ linkml_store/api/stores/solr/solr_collection.py,sha256=ZlxC3JbVaHfSA4HuTeJTsp6qe
 linkml_store/api/stores/solr/solr_database.py,sha256=TFjqbY7jAkdrhAchbNg0E-mChSP7ogNwFExslbvX7Yo,2877
 linkml_store/api/stores/solr/solr_utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/api/types.py,sha256=3aIQtDFMvsSmjuN5qrR2vNK5sHa6yzD_rEOPA6tHwvg,176
-linkml_store/cli.py,sha256=_oDbqElZIWKHJ6ruJyu57rbg2IYUr7U-0AqDlKz6jug,21126
+linkml_store/cli.py,sha256=NIEU5dEkEKz3a2q4mpkdXxHX1mANd2z9oFIkNVz-wsw,27048
 linkml_store/constants.py,sha256=x4ZmDsfE9rZcL5WpA93uTKrRWzCD6GodYXviVzIvR38,112
 linkml_store/graphs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/graphs/graph_map.py,sha256=bYRxv8n1YPnFqE9d6JKNmRawb8EAhsPlHhBue0gvtZE,712
@@ -39,19 +39,31 @@ linkml_store/index/implementations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQe
 linkml_store/index/implementations/llm_indexer.py,sha256=LI5f8SLF_rJY5W6wZPLaUqpyoq-VDW_KqlCBNDNm_po,4827
 linkml_store/index/implementations/simple_indexer.py,sha256=KnkFJtXTHnwjhD_D6ZK2rFhBID1dgCedcOVPEWAY2NU,1282
 linkml_store/index/indexer.py,sha256=K-TDPzdTyGFo6iG4XI_A_3IpwDbKeiTIbdr85NIL5r8,4918
+linkml_store/inference/__init__.py,sha256=b8NAFNZjOYU_8gOvxdyCyoiHOOl5Ai2ckKs1tv7ZkkY,342
+linkml_store/inference/evaluation.py,sha256=qvsmGDBKTZBDKhpbPDe_AkcJ2LtQ8e-oUYCUGfI6IAE,5799
+linkml_store/inference/implementations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+linkml_store/inference/implementations/rag_inference_engine.py,sha256=MH50-6i30Y5oKgIx47-yDjsPCojYC6-lujtHFBDqIxs,5833
+linkml_store/inference/implementations/rule_based_inference_engine.py,sha256=0IEY_fsHJPJy6QKbYQU_qE87RRnPOXQxPuJKXCQG8jU,6250
+linkml_store/inference/implementations/sklearn_inference_engine.py,sha256=HRhwnlpDJOijxvhLmdTSOq1S9xjBVCrgRT1C8uS0XZQ,13196
+linkml_store/inference/inference_config.py,sha256=xgl3VmueErLIOnQQn4HdC2STJNY6yKoPasWmym4ltHQ,2014
+linkml_store/inference/inference_engine.py,sha256=D1JlkihyNbZp7PYe5lplUbTJgyP7jL4vnxcpBio-KUs,6987
+linkml_store/inference/inference_engine_registry.py,sha256=6o66gvBYBwdeAKm62zqqvfaBlcopVP_cla3L6uXGsHA,3015
 linkml_store/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/utils/change_utils.py,sha256=O2rvSvgTKB60reLLz9mX5OWykAA_m93bwnUh5ZWa0EY,471
 linkml_store/utils/file_utils.py,sha256=rQ7-XpmI6_Kx_dhEnI98muFRr0MmgI_kZ_9cgJBf_0I,1411
-linkml_store/utils/format_utils.py,sha256=aBS0uUhvdgPEXzw72iGfSezmHZFnqHtPuFUbVR4cfbA,13174
+linkml_store/utils/format_utils.py,sha256=airJ2_tFsr0dTIbSHT5y0TZbDrvBBV4_qThFPFY5k8U,10925
 linkml_store/utils/io.py,sha256=JHUrWDtlZC2jtN_PQZ4ypdGIyYlftZEN3JaCvEPs44w,884
+linkml_store/utils/llm_utils.py,sha256=Wb4h_E8vrJZDAYHhOdMCSMcz-xxVia4nfuFqiYitZ98,2864
 linkml_store/utils/mongodb_utils.py,sha256=Rl1YmMKs1IXwSsJIViSDChbi0Oer5cBnMmjka2TeQS8,4665
 linkml_store/utils/neo4j_utils.py,sha256=y3KPmDZ8mQmePgg0lUeKkeKqzEr2rV226xxEtHc5pRg,1266
-linkml_store/utils/object_utils.py,sha256=is6T2gruvVKvWD5ZntcAl6Qi3L154FObEho_b_crTuE,2539
-linkml_store/utils/pandas_utils.py,sha256=INL8aZ5v2OeLg-Uzfa8P1cpnMMKA1DumiTB0q175tw8,1389
+linkml_store/utils/object_utils.py,sha256=Vib-5Ip2DlRVKLZpU-008ZZI813-vfKVSCY0TksRenM,6293
+linkml_store/utils/pandas_utils.py,sha256=djiFPO3YbgRVo2XAZuKCtgH8QVLuUyPIsfS8e-0umsU,3182
 linkml_store/utils/patch_utils.py,sha256=q-h_v68okyruzdPTEHCe0WubbQHKpi1qy5bJ9vFWDo8,4823
 linkml_store/utils/query_utils.py,sha256=HWt46BsGWoIGiNBTtvpXGY6onPRWsQky6eu_9cYqbvo,3440
 linkml_store/utils/schema_utils.py,sha256=iJiZxo5NGr7v87h4DV6V9DrDOZHSswMRuf0N4V2rVtg,646
+linkml_store/utils/sklearn_utils.py,sha256=itPpcrsbbyOazdjmivaaZ1lyZeytm0a0hJ2AS8ziUgg,7590
 linkml_store/utils/sql_utils.py,sha256=T41w_vsc3SauTJQkDMwid_nOtKW1YOKyUuaxEf470hk,5938
+linkml_store/utils/stats_utils.py,sha256=4KqBb1bqDgAmq-1fJLLu5B2paPgoZZc3A-gnyVam4bI,1799
 linkml_store/webapi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 linkml_store/webapi/html/__init__.py,sha256=hwp5eeBJKH65Bvv1x9Z4vsT1tLSYtb9Dq4I9r1kL1q0,69
 linkml_store/webapi/html/base.html.j2,sha256=hoiV2uaSxxrQp7VuAZBOHueH7czyJMYcPBRN6dZFYhk,693
@@ -60,8 +72,8 @@ linkml_store/webapi/html/database_details.html.j2,sha256=qtXdavbZb0mohiObI9dvJtk
 linkml_store/webapi/html/databases.html.j2,sha256=a9BCWQYfPeFhdUd31CWhB0yWhTIFXQayO08JgjyqKoc,294
 linkml_store/webapi/html/generic.html.j2,sha256=KtLaO2HUEF2Opq-OwHKgRKetNWe8IWc6JuIkxRPsywk,1018
 linkml_store/webapi/main.py,sha256=B0Da575kKR7X88N9ykm99Dem8FyBAW9f-w3A_JwUzfw,29165
-linkml_store-0.1.13.dist-info/LICENSE,sha256=77mDOslUnalYnuq9xQYZKtIoNEzcH9mIjvWHOKjamnE,1086
-linkml_store-0.1.13.dist-info/METADATA,sha256=ouYb20TN5M2D12IUx9qspIIOiI-6qmrPpe1b6xx9xhU,5609
-linkml_store-0.1.13.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-linkml_store-0.1.13.dist-info/entry_points.txt,sha256=gWxVsHqx-t-UKWFHFzawQTvs4is4vC1rCF5AeKyqWWk,101
-linkml_store-0.1.13.dist-info/RECORD,,
+linkml_store-0.2.0.dist-info/LICENSE,sha256=77mDOslUnalYnuq9xQYZKtIoNEzcH9mIjvWHOKjamnE,1086
+linkml_store-0.2.0.dist-info/METADATA,sha256=v_KjIlu-gTOHunF0ASPHRP_utQv-ry1piX3RpfPWX1k,6743
+linkml_store-0.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+linkml_store-0.2.0.dist-info/entry_points.txt,sha256=gWxVsHqx-t-UKWFHFzawQTvs4is4vC1rCF5AeKyqWWk,101
+linkml_store-0.2.0.dist-info/RECORD,,