ml_approach_suggestion_agent 0.1.0__py3-none-any.whl → 0.1.3__py3-none-any.whl

ml_approach_suggestion_agent/agent.py

@@ -17,7 +17,7 @@ class MLApproachDecisionAgent:
         self.config = config or MethodologyConfig()
         self.ai_handler = SFNAIHandler()
 
-    def suggest_approach(self, domain_name, domain_description, use_case, column_descriptions, column_insights, target_column_name, target_column_insights, max_try=1) -> Tuple[MethodologyRecommendation, Dict[str, Any]]:
+    def suggest_approach(self, domain_name, domain_description, use_case, column_insights, max_try=1) -> Tuple[MethodologyRecommendation, Dict[str, Any]]:
         """
         Suggests a machine learning approach based on the provided domain, use case, and column descriptions.
         Args:
@@ -36,7 +36,7 @@ class MLApproachDecisionAgent:
             
             
         """
-        system_prompt, user_prompt = format_approach_prompt(domain_name=domain_name, domain_description=domain_description, use_case=use_case, column_descriptions=column_descriptions, column_insights=column_insights, target_column_name=target_column_name, target_column_insights=target_column_insights)
+        system_prompt, user_prompt = format_approach_prompt(domain_name=domain_name, domain_description=domain_description, use_case=use_case, column_insights=column_insights)
         for _ in range(max_try):
             try:
                 response, cost_summary = self.ai_handler.route_to(
@@ -66,14 +66,11 @@ class MLApproachDecisionAgent:
 
     def execute_task(self, task_data: Dict[str, Any]) -> Dict[str, Any]:
         self.logger.info("Executing data quality assessment task.")
-        domain_name, domain_description, use_case, column_descriptions, column_insights, target_column_name, target_column_insights = (
+        domain_name, domain_description, use_case, column_insights = (
             task_data["domain_name"],
             task_data["domain_description"],
             task_data["use_case"],
-            task_data["column_descriptions"],
             task_data["column_insights"],
-            task_data["target_column_name"],
-            task_data["target_column_insights"],
         )
 
         # Suggest an approach
@@ -81,10 +78,7 @@ class MLApproachDecisionAgent:
             domain_name=domain_name,
             domain_description=domain_description,
             use_case=use_case,
-            column_descriptions=column_descriptions,
             column_insights=column_insights,
-            target_column_name=target_column_name,
-            target_column_insights=target_column_insights
         )
         if not result:
             return {

ml_approach_suggestion_agent/config.py

@@ -13,7 +13,7 @@ class MethodologyConfig(BaseSettings):
     )
 
     methodology_ai_provider: str = Field(default="openai", description="AI provider to use")
-    methodology_ai_model: str = Field(default="gpt-4o-mini", description="AI model to use")
+    methodology_ai_model: str = Field(default="gpt-5-mini", description="AI model to use")
     methodology_temperature: float = Field(default=0.3, ge=0.0, le=0.5, description="AI model temperature")
     methodology_max_tokens: int = Field(default=4000, ge=100, le=8000, description="Maximum tokens for AI response")
 

ml_approach_suggestion_agent/constants.py

@@ -1,102 +1,84 @@
-METHODOLOGY_SELECTION_SYSTEM_PROMPT = """
-You are an ML methodology advisor. Your task is to analyze the user's problem and recommend the single most appropriate approach.
+METHODOLOGY_SELECTION_SYSTEM_PROMPT = """You are an ML methodology advisor. Analyze the problem and select ONE methodology: binary_classification, time_series_forecasting, or not_applicable.
 
-**Decision Framework:**
+**Simple Decision Rules:**
 
-1. **Understand the Business Goal:** Start with the `use_case_description` to grasp what the user is trying to achieve.
+1. **Binary Classification** - Choose when:
+   - Use case asks "predict whether", "will X happen", "classify if"
+   - Answer is YES/NO, TRUE/FALSE, or 1/0
+   - Example: "predict if machine fails", "detect fraud", "identify churn"
 
-2. **Examine the Target Variable:** Use `target_column_insights` to understand the nature of what needs to be predicted:
-   - Check `unique_count` to determine if it's binary (2 values), multiclass (>2 values), or continuous
-   - Check `data_type` to see if it's numerical (int/float) or categorical (str)
-   - Review `sample_values` to understand the actual values
+2. **Time Series Forecasting** - Choose when:
+   - Use case asks to "forecast", "predict future value", "estimate next"
+   - Answer is a NUMERICAL value in the FUTURE
+   - Example: "forecast next month sales", "predict tomorrow's temperature"
 
-3. **Check for Temporal Dependencies:** Look for these indicators in `column_insights`:
-   - Presence of timestamp/date columns with high unique_count (near row_count)
-   - Column descriptions mentioning "time", "date", "timestamp", "sequential"
-   - Use case description mentioning "over time", "forecast", "predict future", "trend", "sequential patterns"
-   - If temporal column exists AND the prediction depends on historical patterns, consider time series methods
-
-4. **Critical Time Series Distinction:**
-   - **Time Series Forecasting**: Target is NUMERICAL and goal is predicting FUTURE VALUES (e.g., "predict next month's sales", "forecast temperature")
-   - **Time Series Classification**: Target is CATEGORICAL (even if binary 0/1) and data is SEQUENTIAL (e.g., "classify failure from sensor patterns", "detect activity type from accelerometer sequence")
-   - **Binary/Multiclass Classification**: Target is categorical BUT data points are INDEPENDENT (no temporal ordering matters)
-
-5. **Assess Data Structure:** Review `column_insights`:
-   - If no target specified or target_column_name is "Not specified" → likely `not_applicable`
-   - If use case is purely computational/rule-based → `not_applicable`
-
-6. **Select ONE Methodology:**
-   - `binary_classification`: Target has exactly 2 unique values (categorical/binary) AND samples are independent (no temporal dependency)
-   - `multiclass_classification`: Target has >2 unique categories AND samples are independent
-   - `time_series_forecasting`: Target is NUMERICAL AND prediction involves FUTURE time periods based on historical patterns
-   - `time_series_classification`: Target is CATEGORICAL (binary or multiclass) AND data has TEMPORAL ORDERING where sequential patterns are critical for prediction
-   - `not_applicable`: No clear ML objective, purely rule-based problem, or insufficient information
-
-7. **Key Rules to Avoid Mistakes:**
-   - Binary target (0/1) with timestamp does NOT automatically mean binary_classification - check if SEQUENCE matters
-   - If use case mentions "based on sensor readings over time", "sequential patterns", "time-series data" → it's time_series_classification
-   - If use case is just "predict X" with no temporal context and independent samples → it's binary/multiclass_classification
-   - Presence of timestamp column alone doesn't mean time series - check if the PREDICTION depends on temporal patterns
-   - If target is numerical but goal is "classify into categories" → still classification, not regression
-
-8. **Justify Your Choice:** 
-   - State the business goal clearly
-   - Identify the target variable type (binary/multiclass/numerical)
-   - Explain whether temporal dependencies exist and matter for prediction
-   - Connect these factors to show why the chosen methodology fits
+3. **Not Applicable** - Choose when:
+   - No prediction needed
+   - Just data analysis, reporting, or calculations
+   - Not enough information
+**Required Output:**
+1. Select the single best ML methodology from: binary_classification, time_series_forecasting, or not_applicable
+2. Provide a clear justification explaining:
+   - What you understand the business goal to be
+   - What type of prediction is needed (binary outcome, numerical forecast, or none)
+   - Whether temporal patterns are critical for this prediction
+   - Why the selected methodology is the best fit
 
+**Important:**
+- Having timestamps doesn't mean it's time series forecasting
+- Check WHAT is being predicted: binary outcome OR future number
+- The dataset may contain 1-4 tables - analyze all provided tables together"""
 
-"""
 
 
-
-METHODOLOGY_SELECTION_USER_PROMPT = """
-**Business Context:**
+METHODOLOGY_SELECTION_USER_PROMPT = """**Business Context:**
 Domain: {domain_name}
 {domain_description}
 
 **Use Case:**
 {use_case_description}
 
-**Data Overview:**
-Columns:
-{column_descriptions}
 
 Dataset Characteristics:
 {column_insights}
 
-**Target Information:**
-Target Column: {target_column_name}
-Target Details: {target_column_insights}
-
-**Required Output:**
-1. Select the single best ML methodology
-2. Provide a brief justification explaining why this methodology fits the problem
 """
 
 
-
-def format_approach_prompt(domain_name, domain_description, use_case, column_descriptions, column_insights, target_column_name, target_column_insights):
+def format_approach_prompt(
+    domain_name: str,
+    domain_description: str,
+    use_case: str,
+    column_insights: str
+) -> tuple[str, str]:
     """
+    Format the methodology selection prompts for the LLM.
+    
     Args:
-    domain (str): The domain of the data.
-    use_case (str): The use case of the data.
-    column_descriptions (List[str]): A list of column descriptions.
-    column_insights (List[str]): A list of column insights.
-
+        domain_name: The domain of the data (e.g., "Healthcare", "Finance")
+        domain_description: Detailed description of the domain context
+        use_case: Description of what the user wants to achieve
+        column_descriptions: Description of the columns in the dataset
+        column_insights: Statistical insights about the columns (data types, 
+                        unique counts, distributions, etc.)
+    
     Returns:
-    Tuple[str, str]: The formatted system prompt and user prompt.
-    TODO: 
-        - Change prompt write new prompt and involve the supported approaches in new prompt.
+        tuple[str, str]: The formatted system prompt and user prompt
+    
+    Example:
+        system_prompt, user_prompt = format_approach_prompt(
+            domain_name="E-commerce",
+            domain_description="Online retail platform with customer transactions",
+            use_case="Predict if a customer will make a purchase",
+            column_descriptions="user_id, page_views, cart_additions, timestamp",
+            column_insights="4 columns, 10000 rows, mixed types"
+        )
     """
-
     user_prompt = METHODOLOGY_SELECTION_USER_PROMPT.format(
         domain_name=domain_name,
         domain_description=domain_description,
         use_case_description=use_case,
-        column_descriptions=column_descriptions,
-        column_insights=column_insights,
-        target_column_name=target_column_name,
-        target_column_insights=target_column_insights,
+        column_insights=column_insights
     )
-    return METHODOLOGY_SELECTION_SYSTEM_PROMPT, user_prompt
+    
+    return METHODOLOGY_SELECTION_SYSTEM_PROMPT, user_prompt

ml_approach_suggestion_agent/models.py

@@ -2,6 +2,6 @@ from pydantic import BaseModel, Field
 from typing import Literal
 
 class MethodologyRecommendation(BaseModel):
-    selected_methodology: Literal["binary_classification", "multiclass_classification", "time_series_forecasting", "time_series_classification", "not_applicable" ] = Field(..., description="The most appropriate ML approach for this problem")
+    selected_methodology: Literal[ "binary_classification", "time_series_forecasting", "not_applicable"] = Field(..., description="The most appropriate ML approach for this problem")
     
-    justification: str = Field(..., description="Clear explanation connecting the business goal and target variable to the chosen methodology")
+    justification: str = Field( ..., description="Clear explanation connecting the business goal and data characteristics to the chosen methodology")

{ml_approach_suggestion_agent-0.1.0.dist-info → ml_approach_suggestion_agent-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ml_approach_suggestion_agent
-Version: 0.1.0
+Version: 0.1.3
 Summary: Add your description here
 License-Expression: MIT
 Classifier: Programming Language :: Python :: 3
@@ -12,7 +12,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: pydantic-settings
-Requires-Dist: sfn-blueprint>=0.6.15
+Requires-Dist: sfn-blueprint>=0.6.16
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-mock; extra == "dev"

ml_approach_suggestion_agent-0.1.3.dist-info/RECORD

@@ -0,0 +1,9 @@
+ml_approach_suggestion_agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ml_approach_suggestion_agent/agent.py,sha256=HdISZ15vU5K7pzHXJpncrCWpgPvEGJLn7_1jTt7Zeuw,5010
+ml_approach_suggestion_agent/config.py,sha256=19zO13zQ2Fmf_0wKqOfc2KfM-WD6EM4YPJLjRrG_jTY,703
+ml_approach_suggestion_agent/constants.py,sha256=EDLzMHXM8lwxb-lVLjkVElCJYChPntXW06WfCQHglJ8,3139
+ml_approach_suggestion_agent/models.py,sha256=cfZbMZPMAcNxeWTuIb_TKmNSr0C99Z4ZMicYPxlScyA,448
+ml_approach_suggestion_agent-0.1.3.dist-info/METADATA,sha256=tdnDGRvv6_VEkgkvLKTe6XcV_qfLiKNB2IE5LOdqD4c,8451
+ml_approach_suggestion_agent-0.1.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ml_approach_suggestion_agent-0.1.3.dist-info/top_level.txt,sha256=3-KHls6umFXtNFJoP7OFCLvb4zd12AWH71PVKNd5Aok,29
+ml_approach_suggestion_agent-0.1.3.dist-info/RECORD,,

ml_approach_suggestion_agent-0.1.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-ml_approach_suggestion_agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ml_approach_suggestion_agent/agent.py,sha256=4FgDbiFXY1BRQN3hToif2Y-uaceHPdPrwyG3GEVRWMU,5569
-ml_approach_suggestion_agent/config.py,sha256=YOAXgdzgY72yB0mNEt9J2w1bdavx-VSCANBJ_4YR4Bo,704
-ml_approach_suggestion_agent/constants.py,sha256=znbt7x6xAxJL4eAZXcr8njerD84c8QuKK2ZlsFhsloo,5011
-ml_approach_suggestion_agent/models.py,sha256=i4vxGvA9vB3JOAh8IySMfcyAEQ7CWQe9ArgG7Rqo_cU,501
-ml_approach_suggestion_agent-0.1.0.dist-info/METADATA,sha256=qha4KlPfYbnoPlkCSJM_1L0COCFeh0CxBC_sr2WLYU0,8451
-ml_approach_suggestion_agent-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ml_approach_suggestion_agent-0.1.0.dist-info/top_level.txt,sha256=3-KHls6umFXtNFJoP7OFCLvb4zd12AWH71PVKNd5Aok,29
-ml_approach_suggestion_agent-0.1.0.dist-info/RECORD,,