updated examples for csv data source on ahu ipynb. still working on b…

…rick method

README.md

@@ -30,17 +30,18 @@ The following are key objectives to enhance this project into a fully interactiv
 
 ### In Progress
  - [ ] Create IPython notebook tutorials showcasing AHU FDD examples, incorporating BRICK metadata integration.
- - [ ] Develop a comprehensive guide on a github.io website (or other?) for defining fault parameters, including error thresholds and other critical settings.
+ - [ ] Extend the project to include `central_plant` fault conditions, IPython reports, and example applications for boiler and chiller systems.
+
 
 ### Upcoming
- - [ ] Extend the project to include `central_plant` fault conditions, IPython reports, and example applications.
  - [ ] Design `energy_efficiency` fault detection modules, including IPython reports and examples focused on optimizing energy consumption.
  - [ ] Develop `metering` fault conditions, along with IPython reports and examples, potentially modeling utility metering data.
  - [ ] Implement SQL integration examples for reading data from a time series database, writing back to SQL, and visualizing faults in Grafana.
 
 ### Future Considerations
  Explore additional features and enhancements as the project evolves.
  - [ ] Explore additional features and enhancements as the project evolves.
+ - [ ] Develop a comprehensive guide on a github.io website (or other?) for defining fault parameters, including error thresholds and other critical settings.
 
 
 ## Contribute

examples/brick_model_and_sqlite/1_make_db.py

@@ -1,5 +1,6 @@
 import sqlite3
 import pandas as pd
+import re
 
 # Step 1: Connect to SQLite database (or create it)
 conn = sqlite3.connect("brick_timeseries.db")
@@ -48,30 +49,49 @@
 )
 
 # Step 4: Load the CSV data
-csv_file = r"C:\Users\bbartling\Documents\WPCRC_July.csv"
+csv_file = r"C:\Users\bbartling\Documents\brick_data_July_2024.csv"
 df = pd.read_csv(csv_file)
-print("df.columns", df.columns)
+print("Original df.columns", df.columns)
 
 # Ensure that the 'timestamp' column is properly parsed as a datetime object
 if "timestamp" in df.columns:
     df["timestamp"] = pd.to_datetime(df["timestamp"])
 else:
     raise ValueError("The CSV file does not contain a 'timestamp' column.")
 
-print("Starting step 5")
+# Step 4.1: Remove specific strings from the tail of the sensor names using regex
+pattern = (
+    r"(\/|inwc|\(\)|galmin|\(%\)|\(°F\)|\(A\)|\(Δpsi\)|\(cfm\)|\(in\/wc\)|\(gal\/min\))"
+)
+df.columns = df.columns.str.replace(pattern, "", regex=True)
+
+# Print columns after modification to verify changes
+print("Modified df.columns", df.columns)
 
 # Step 5: Insert CSV data into the TimeseriesData table
 for column in df.columns:
     if column != "timestamp":  # Skip the timestamp column itself
-        for index, row in df.iterrows():
-            cursor.execute(
-                """
-            INSERT INTO TimeseriesData (sensor_name, timestamp, value)
-            VALUES (?, ?, ?)
-            """,
-                (column, row["timestamp"].strftime("%Y-%m-%d %H:%M:%S"), row[column]),
-            )
-        print(f"Doing {column} in step 5")
+        # Only process columns related to AHU fan VFD speed, static pressure sensor, and setpoint
+        if "StaticSPt" in column or "SaStatic" in column or "SaFanSpeedAO" in column:
+            for index, row in df.iterrows():
+                cursor.execute(
+                    """
+                INSERT INTO TimeseriesData (sensor_name, timestamp, value)
+                VALUES (?, ?, ?)
+                """,
+                    (
+                        column,
+                        row["timestamp"].strftime("%Y-%m-%d %H:%M:%S"),
+                        row[column],
+                    ),
+                )
+                if index < 5:  # Print the first 5 rows only
+                    print(
+                        f"Inserted sensor name {column} with value {row[column]} at {row['timestamp']}"
+                    )
+            print(f"Processed {column} in step 5")
+        else:
+            pass
 
 conn.commit()
 
@@ -80,15 +100,18 @@
 # Step 6: Insert timeseries references based on sensor names
 for column in df.columns:
     if column != "timestamp":  # Skip the timestamp column itself
-        cursor.execute(
-            """
-        INSERT INTO TimeseriesReference (timeseries_id, stored_at)
-        VALUES (?, ?)
-        """,
-            (column, "SQLite Timeseries Storage"),
-        )
-
-        print(f"Doing {column} in step 6")
+        # Only process columns related to AHU fan VFD speed, static pressure sensor, and setpoint
+        if "StaticSPt" in column or "SaStatic" in column or "SaFanSpeedAO" in column:
+            cursor.execute(
+                """
+            INSERT INTO TimeseriesReference (timeseries_id, stored_at)
+            VALUES (?, ?)
+            """,
+                (column, "SQLite Timeseries Storage"),
+            )
+            print(f"Inserted reference for {column} in step 6")
+        else:
+            pass
 
 conn.commit()