feat: access data

src/production/flow.py

@@ -12,8 +12,7 @@ def generate_data(state):
     """
     current_time = state["current_time"] if state["current_time"] else datetime.now()
     part_id = state["part_id"] if state["part_id"] else 0
-    if 'raw' not in state['data']:
-        state['data']['raw'] = []
+
     non_compliance_rates = {
         1: 0.05,
         2: 0.10,
@@ -21,6 +20,14 @@ def generate_data(state):
         4: 0.07
     }
 
+    # Initialize raw_df if it doesn't exist
+    if 'raw_df' not in state['data']:
+        state['data']['raw_df'] = pd.DataFrame(columns=[
+            "Part ID", "Timestamp", "Position", "Orientation", "Tool ID",
+            "Compliance", "Event", "Error Code", "Error Description",
+            "Downtime Start", "Downtime End"
+        ])
+
     for _ in range(1000):
         if not state["running"]:
             break
@@ -30,14 +37,21 @@ def generate_data(state):
             error = machine_errors[error_key]
             downtime = error["downtime"]
 
-            state['data']['raw'].append({
-                "timestamp": current_time.strftime("%Y-%m-%d %H:%M:%S"),
-                "event": "Machine Error",
-                "error_code": error_key,
-                "error_description": error["description"],
-                "downtime_start": current_time.strftime("%Y-%m-%d %H:%M:%S"),
-                "downtime_end": (current_time + downtime).strftime("%Y-%m-%d %H:%M:%S")
-            })
+            new_row = pd.DataFrame([{
+                "Part ID": "N/A",
+                "Timestamp": current_time.strftime("%Y-%m-%d %H:%M:%S"),
+                "Position": "N/A",
+                "Orientation": "N/A",
+                "Tool ID": "N/A",
+                "Compliance": "N/A",
+                "Event": "Machine Error",
+                "Error Code": error_key,
+                "Error Description": error["description"],
+                "Downtime Start": current_time.strftime("%Y-%m-%d %H:%M:%S"),
+                "Downtime End": (current_time + downtime).strftime("%Y-%m-%d %H:%M:%S")
+            }])
+
+            state['data']['raw_df'] = pd.concat([state['data']['raw_df'], new_row], ignore_index=True)
 
             current_time += downtime
         else:
@@ -51,14 +65,21 @@ def generate_data(state):
 
             compliance = 'OK' if (0.3 <= position <= 0.5) and (0.2 <= orientation <= 0.6) else 'NOK'
 
-            state['data']['raw'].append({
-                "part_id": part_id,
-                "timestamp": current_time.strftime("%Y-%m-%d %H:%M:%S"),
-                "position": round(position, 4),
-                "orientation": round(orientation, 4),
-                "tool_id": tool_id,
-                "compliance": compliance
-            })
+            new_row = pd.DataFrame([{
+                "Part ID": part_id,
+                "Timestamp": current_time.strftime("%Y-%m-%d %H:%M:%S"),
+                "Position": round(position, 4),
+                "Orientation": round(orientation, 4),
+                "Tool ID": tool_id,
+                "Compliance": compliance,
+                "Event": "N/A",
+                "Error Code": "N/A",
+                "Error Description": "N/A",
+                "Downtime Start": "N/A",
+                "Downtime End": "N/A"
+            }])
+
+            state['data']['raw_df'] = pd.concat([state['data']['raw_df'], new_row], ignore_index=True)
 
             print(f"     - part {part_id} data generated")
             part_id += 1
@@ -67,22 +88,4 @@ def generate_data(state):
         current_time += timedelta(seconds=1)
 
     state["current_time"] = current_time
-    state["part_id"] = part_id
-
-    raw_data = []
-    for row in state['data']['raw']:
-        raw_data.append({
-            "Part ID": row.get("part_id", "N/A"),
-            "Timestamp": row.get("timestamp", "N/A"),
-            "Position": row.get("position", "N/A"),
-            "Orientation": row.get("orientation", "N/A"),
-            "Tool ID": row.get("tool_id", "N/A"),
-            "Compliance": row.get("compliance", "N/A"),
-            "Event": row.get("event", "N/A"),
-            "Error Code": row.get("error_code", "N/A"),
-            "Error Description": row.get("error_description", "N/A"),
-            "Downtime Start": row.get("downtime_start", "N/A"),
-            "Downtime End": row.get("downtime_end", "N/A")
-        })
-
-    state['data']['raw_df'] = pd.DataFrame(raw_data)
+    state["part_id"] = part_id

src/production/metrics/machine.py

@@ -2,7 +2,7 @@ import pandas as pd
 import json
 import os
 
-def get_machine_metrics(raw_data):
+def machine_metrics(raw_data):
     """
     Calculate machine efficiency metrics from raw production data.
     :param raw_data: collection of raw production data containing timestamps, downtime, and compliance information.
@@ -62,4 +62,9 @@ def get_machine_metrics(raw_data):
         "TRS": TRS,
         "MTBF": str(mtbf),
         "MTTR": str(mttr)
-    }
+    }
+
+def fetch_issues(raw_data):
+    df = pd.DataFrame(raw_data)
+    issues = df[df["Event"] == "Machine Error"]
+    return issues[["Timestamp", "Event", "Error Code", "Error Description", "Downtime Start", "Downtime End"]]

src/production/metrics/tools.py

@@ -35,7 +35,7 @@ def process_unique_tool(tool, raw_data):
     return tool, tool_data
 
 
-def get_tools_metrics(raw_data):
+def tools_metrics(raw_data):
     """
     Process the raw production data to extract tool metrics in parallel.
     """