chore: bump version to 1.0.15

mlModelSaver/__init__.py

@@ -77,6 +77,18 @@ class MlModelSaver:
         self.modelsFolder = f'{self.baseRelativePath}/{config.get('modelsFolder', '~~modelsFolder')}'
         ensure_directory_exists(self.modelsFolder)
 
+    def listOfPickels(self):
+        files = os.listdir(self.modelsFolder)
+        pickelsList = [file for file in files if file.endswith('.pkl')]
+        return pickelsList
+
+    def listOfModels(self):
+        pickelsList = self.listOfPickels()
+        modelsList = []
+        for pickekFileName in pickelsList:
+            modelsList.append(pickekFileName.split(".pkl")[0])
+        return modelsList
+
 
 
     def showSupportedModels(self):
@@ -102,3 +114,5 @@ class MlModelSaver:
         loaded_model = pickle.load(open(filename, 'rb'))
         self.cachedModels[loaded_model.mlModelSaverConfig.get("modelName")] = loaded_model
         return loaded_model
+
+

package.json

@@ -1,6 +1,6 @@
 {
   "name": "mlModelSaver",
-  "version": "1.0.14",
+  "version": "1.0.15",
   "description": "Make life easier for save and serving ml models",
   "main": "index.js",
   "repository": "git@github.com:smartdev-ca/mlModelSaver.git",

pytests/test_mlModelSaver.py

@@ -1,82 +1,128 @@
-# test_mlModelSaver.py
+import pickle
+import json
 
-import sys
 import os
 
-sys.path.insert(
+from functools import partial
-    0,
+
-    os.path.abspath(
+def ensure_directory_exists(directory_path):
-        os.path.join(
+    """
-            os.path.dirname(__file__),
+    Ensure that the specified directory exists. If it doesn't, create it.
-            '..'
+
-        )
+    Parameters:
-    )
+    directory_path (str): The path of the directory to ensure exists.
-)
+    """
+    os.makedirs(directory_path, exist_ok=True)
 
 
-def test_ensureCLassInstance():
+def check_file_exists(file_path):
-    from mlModelSaver import MlModelSaver
+    """
-    mlModelSaverInstance1 = MlModelSaver({
+    Check if the specified file exists.
-        "baseRelativePath": "test_baseRelativePath",
+
-        "modelsFolder": "test_modelsFolder"
+    Parameters:
-    })
+    file_path (str): The path of the file to check.
-    assert mlModelSaverInstance1.baseRelativePath == "test_baseRelativePath"
+
-    assert mlModelSaverInstance1.modelsFolder == "test_baseRelativePath/test_modelsFolder"
+    Returns:
-    tesSupportedModels = mlModelSaverInstance1.showSupportedModels()
+    bool: True if the file exists, False otherwise.
-    assert tesSupportedModels == ['sm.OLS']
+    """
+    if os.path.isfile(file_path):
+        print(f"File '{file_path}' exists.")
+        return True
+    else:
+        print(f"File '{file_path}' does not exist.")
+        return False
 
 
-def test_OLS_LinearRegression():
+supportedModels = {
-    from mlModelSaver import MlModelSaver
+    "sm.OLS": {
-    import numpy as np
+        "supported": True
-    import pandas as pd
+    }
-    import statsmodels.api as sm
+}
-    from helpers import add_constant_column
+
-    salaryMisDf = pd.read_excel("./datasets/Salary_MIS.xlsx")
+supportedDataType = {
-    salaryBasedOnGpaMisStatistics = sm.OLS(
+    "int": {
-        salaryMisDf["Salary"],
+        "supported": True
-        add_constant_column(salaryMisDf[["GPA", "MIS", "Statistics"]])
+    },
-    )
+    "float": {
-    salaryBasedOnGpaMisStatisticsFit = salaryBasedOnGpaMisStatistics.fit()
+        "supported": True
-    mlModelSaverInstance2 = MlModelSaver({
+    },
-        "baseRelativePath": ".",
+    "binary":{
-        "modelsFolder": "~~tmp/testModels"
+        "supported": True
-    })
+    }
+}
+
+def default_transformer(x):
+    return x
+
+
+def mlModelSavePredict(self, df, typeOfPredict = 'normal'):
+    dfAfterTransformation = self.mlModelSaverTransformer(df)
+    output = []
+    outputsName = self.mlModelSaverConfig.get("outputs", [{"name": "result"}])
+    outputsName = [item["name"] for item in outputsName]
+    if typeOfPredict == 'normal':
+        results = self.predict(dfAfterTransformation)
+        for  value in results:
+            output.append({
+                outputsName[0]: value,
+            })
+        return output
+
+class MlModelSaver:
+
+    cachedModels = {}
+
+    def __init__(self, config):
+        self.baseRelativePath = config.get('baseRelativePath', '.')
+        self.modelsFolder = f'{self.baseRelativePath}/{config.get('modelsFolder', '~~modelsFolder')}'
+        ensure_directory_exists(self.modelsFolder)
+
+    def listOfPickles(self):
+        files = os.listdir(self.modelsFolder)
+        picklesList = [file for file in files if file.endswith('.pkl')]
+        return picklesList
+
+    def listOfModels(self):
+        picklesList = self.listOfPickles()
+        modelsList = []
+        for pickleFileName in picklesList:
+            modelsList.append(pickleFileName.split(".pkl")[0])
+        return modelsList
 
 
 
-    loadedModel = mlModelSaverInstance2.exportModel(
+    def showSupportedModels(self):
-        salaryBasedOnGpaMisStatisticsFit,
+        supported_keys = [key for key, value in supportedModels.items() if value.get('supported')]
-        {
+        return supported_keys
-            "modelName": "salaryBasedOnGpaMisStatistics",
+
-            "description": "Predict Salary based on GPA MIS Statistics for salaryMisDf",
+    def loadModelByName(self, modelName):
-            "modelType": "sm.OLS",
+        filename = f'{self.modelsFolder}/{modelName}.pkl'
-            "inputs": [
+        loaded_model = pickle.load(open(filename, 'rb'))
-                {
+        self.cachedModels[loaded_model.mlModelSaverConfig.get("modelName")] = loaded_model
-                    "name": "GPA",
+        return loaded_model
-                    "type": "float",
+
-                },
+    def exportModel(self, model, config):
-                {
+        transformer = config.get("transformer", default_transformer)
-                    "name": "MIS",
+        model.mlModelSaverTransformer = transformer
-                    "type": "binary"
+        if "transformer" in config:
-                },
+            del config["transformer"]
-                {
+        model.mlModelSaverConfig = config
-                    "name": "Statistics",
+        isModelSupporter = supportedModels.get(
-                    "type": "binary"
+            config.get("modelType", ''),
-                }
+            {}
-            ],
+        ).get("supported", False)
-            "transformer": add_constant_column,
+        if not isModelSupporter:
-            "outputs": [
+            raise ValueError(f'only {self.showSupportedModels()} are supported and {config.get("modelType", '')} is not supported')
-                {
+        modelName = model.mlModelSaverConfig['modelName']
-                    "name": "Salary",
+        model.mlModelSavePredict = partial(mlModelSavePredict, model)
-                    "type": "int"
+        filename = f'{self.modelsFolder}/{modelName}.pkl'
-                }
+        pickle.dump(model, open(filename, 'wb'))
-            ]
+        return self.loadModelByName(modelName)
-        }
+
-    )
+    def getModel(self, modelName):
-    from mlModelSaver import check_file_exists
+        model = self.cachedModels.get(modelName, None)
-    assert check_file_exists("./~~tmp/testModels/salaryBasedOnGpaMisStatistics.pkl") == True
+        if model != None:
-    testData = salaryMisDf[["GPA", "MIS", "Statistics"]].iloc[0:2]
+            return model
-    predictedValueWithLoadedModel = loadedModel.mlModelSavePredict(testData, 'normal')
+        return self.loadModelByName(modelName)
-    assert  predictedValueWithLoadedModel == [{'Salary': 73.9924679451542}, {'Salary': 69.55525482441558}]
+
-    assert list(mlModelSaverInstance2.cachedModels.keys()) == ['salaryBasedOnGpaMisStatistics']
+

setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='mlModelSaver',
-    version='1.0.14',
+    version='1.0.15',
     packages=find_packages(),
     description='Make life easier for saving and serving ML models',
     long_description=open('DOCS.md').read(),  # Assumes you have a README.md file