Copy files from vmodak/pdm_aiq_agent to cleaned branch

industries/manufacturing/predictive_maintenance_agent/eval_data/eval_set_master.json

@@ -0,0 +1,232 @@
+[
+  {
+    "id": "1",
+    "question": "What is the remaining useful life (RUL) of unit_number 59 in dataset FD001",
+    "answer": "114 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "1",
+    "source": "eval_set"
+  },
+  {
+    "id": "2",
+    "question": "What is the RUL of unit_number 20 in dataset FD001",
+    "answer": "16 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "2",
+    "source": "eval_set"
+  },
+  {
+    "id": "3",
+    "question": "How many units have RUL of 100 or more in dataset FD003",
+    "answer": "33 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "3",
+    "source": "eval_set"
+  },
+  {
+    "id": "4",
+    "question": "How many units have RUL of 50 or less in dataset FD002",
+    "answer": "88 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "4",
+    "source": "eval_set"
+  },
+  {
+    "id": "5",
+    "question": "Report the unit_number of the units that have RUL equal to 155 in FD002",
+    "answer": "6, 141, 165 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "5",
+    "source": "eval_set"
+  },
+  {
+    "id": "6",
+    "question": "In the dataset FD004, how many units have RUL equal to 10 and what are their unit numbers?",
+    "answer": "4 units; unit numbers: 40, 82, 174, 184",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "6",
+    "source": "eval_set"
+  },
+  {
+    "id": "7",
+    "question": "In dataset train_FD004, what was the operational_setting_3 at time_in_cycles 20 for unit_number 107",
+    "answer": "100 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "7",
+    "source": "eval_set"
+  },
+  {
+    "id": "8",
+    "question": "In dataset train_FD004, what was the 3rd operational setting at time 20 for unit_number 107",
+    "answer": "100 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "8",
+    "source": "eval_set"
+  },
+  {
+    "id": "9",
+    "question": "In dataset test_FD002, what are the values of the three operational setting for unit_number 56 at time_in_cycles 10",
+    "answer": "10.0026, 0.25, 100 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "9",
+    "source": "eval_set"
+  },
+  {
+    "id": "10",
+    "question": "In dataset test_FD003, what is the value of sensor_measurement_4 for unit_number 25 at time_in_cycles 20",
+    "answer": "1409.26 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "10",
+    "source": "eval_set"
+  },
+  {
+    "id": "11",
+    "question": "How many units have operational_setting_3 equal to 100 in dataset train_FD001 at time_in_cycles 40?",
+    "answer": "100 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "aggregation",
+    "original_id": "11",
+    "source": "eval_set"
+  },
+  {
+    "id": "12",
+    "question": "How many units have operational_setting_3 equal to 100 in dataset train_FD001?",
+    "answer": "100 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "aggregation",
+    "original_id": "12",
+    "source": "eval_set"
+  },
+  {
+    "id": "13",
+    "question": "In dataset train_FD003, what was sensor_measurement_20 and sensor_measurement_21 for unit 1 at time_in_cycles 10",
+    "answer": "38.94, 23.4781 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "13",
+    "source": "eval_set"
+  },
+  {
+    "id": "14",
+    "question": "Using the data in test_FD002, predict the remaining useful life of unit_number 10 at time_in_cycles 84",
+    "answer": "79 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "14",
+    "source": "eval_set"
+  },
+  {
+    "id": "15",
+    "question": "Given the data in test_FD003, predict the RUL of unit_number 30",
+    "answer": "89 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "prediction",
+    "original_id": "15",
+    "source": "eval_set"
+  },
+  {
+    "id": "16",
+    "question": "For dataset test_FD004, what is the remaining useful life of unit 60",
+    "answer": "139 ",
+    "category": "text",
+    "type": "data_query",
+    "subcategory": "lookup",
+    "original_id": "16",
+    "source": "eval_set"
+  },
+  {
+    "id": "17",
+    "question": "In dataset train_FD004, plot sensor_measurement1 vs time_in_cycles for unit_number 107",
+    "answer": "Line chart showing sensor_measurement1 values ranging from 445.00 to 518.67 plotted against time_in_cycles for unit 107 in dataset FD004. Should contain 183 data points showing the sensor reading progression over time cycles. The plot should show a time series with sensor measurement values on the y-axis and time in cycles on the x-axis.",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "time_series",
+    "original_id": "1",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "18",
+    "question": "In dataset train_FD004, plot the variation of sensor_measurement1 over time for unit_number 107",
+    "answer": "Line chart displaying the variation of sensor_measurement1 over time cycles for unit 107 in dataset FD004. Should show 183 data points with sensor values ranging from 445.00 to 518.67. The plot should illustrate how sensor_measurement1 changes across different time cycles, demonstrating the temporal variation pattern of this sensor reading.",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "time_series",
+    "original_id": "2",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "19",
+    "question": "In dataset train_FD002, plot operational_setting_3 vs time_in_cycles for unit_number 200",
+    "answer": "Only two values 100 and 60 in the plot",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "time_series",
+    "original_id": "3",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "20",
+    "question": "Plot a histogram showing distribution of values of operational_setting_3 over time for unit_number 200 in dataset train_FD002",
+    "answer": "Two bars for 100 and 60 with higher bar for 100",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "distribution",
+    "original_id": "4",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "21",
+    "question": "In dataset test_FD001 plot a histogram showing the distribution of operational_setting_3 across all units",
+    "answer": "Constant value 100, so just one high bar for 100",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "distribution",
+    "original_id": "5",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "22",
+    "question": "In dataset test_FD001 plot operational_setting_3 as a function of time_in_cycles for units 10, 20, 30, 40",
+    "answer": "Four constant lines at 100",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "time_series",
+    "original_id": "6",
+    "source": "eval_set_plots"
+  },
+  {
+    "id": "23",
+    "question": "Retrieve RUL of all units from the FD001 and plot their distribution using a histogram",
+    "answer": "Histogram showing distribution of RUL values for all units in FD001 dataset. Should contain 100 data points representing different RUL values ranging from 7 to 145 cycles. The distribution should show 71 unique RUL values with varying frequencies. The plot should display the spread and frequency of remaining useful life values across all engine units in the dataset.",
+    "category": "plotting",
+    "type": "visualization",
+    "subcategory": "distribution",
+    "original_id": "7",
+    "source": "eval_set_plots"
+  }
+]

industries/manufacturing/predictive_maintenance_agent/golden_plot_generator/__init__.py

@@ -0,0 +1 @@
+# Golden Plot Generator - Independent plotting system for evaluation 

industries/manufacturing/predictive_maintenance_agent/golden_plot_generator/database/connector.py

@@ -0,0 +1,45 @@
+"""
+Direct SQLite database connector for golden plot generation.
+No dependencies on the agentic framework.
+"""
+import sqlite3
+import pandas as pd
+import os
+from typing import Optional
+
+class DatabaseConnector:
+    def __init__(self, db_path: str = "../PredM_db/nasa_turbo.db"):
+        self.db_path = db_path
+
+    def execute_query(self, sql_query: str) -> Optional[pd.DataFrame]:
+        """
+        Execute SQL query and return results as pandas DataFrame.
+
+        Args:
+            sql_query (str): SQL query to execute
+
+        Returns:
+            pd.DataFrame or None: Query results
+        """
+        try:
+            if not os.path.exists(self.db_path):
+                raise FileNotFoundError(f"Database not found at: {self.db_path}")
+
+            with sqlite3.connect(self.db_path) as conn:
+                df = pd.read_sql_query(sql_query, conn)
+                return df
+
+        except Exception as e:
+            print(f"Error executing query: {e}")
+            print(f"SQL Query: {sql_query}")
+            return None
+
+    def get_table_info(self, table_name: str) -> Optional[pd.DataFrame]:
+        """Get table schema information."""
+        sql = f"PRAGMA table_info({table_name})"
+        return self.execute_query(sql)
+
+    def list_tables(self) -> Optional[pd.DataFrame]:
+        """List all tables in the database."""
+        sql = "SELECT name FROM sqlite_master WHERE type='table'"
+        return self.execute_query(sql)