eda.py

@@ -95,7 +95,7 @@ def plot_daily_mean_power(data):
 # Main Program to run the clustering
 if __name__ == "__main__":
     # Load the dataset
-    data = pd.read_csv("/home/jvaldes/Desktop/krishna-thesis/thesiscodeimplementation/data/Autohaus 2.csv")  # Replace with your dataset file
+    data = pd.read_csv("/home/jvaldes/Desktop/krishna-thesis/thesiscodeimplementation/data/eth_data/EFH (8).csv")  # Replace with your dataset file
 
     #df = exploratory_data_analysis(data)
     plot_daily_mean_power(data)

plot_original_data.py

+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import glob
+import os
+
+# Define a color palette for 12 months
+months = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
+colors = sns.color_palette("tab10", 12)
+month_color_map = dict(zip(range(1, 13), colors))
+
+# Load all CSV files (assumed to be in the current directory)
+file_paths = glob.glob("/home/jvaldes/Desktop/krishna-thesis/thesiscodeimplementation/data/fenecon_de/*.csv")  # Adjust the path accordingly
+
+plt.figure(figsize=(12, 6))
+
+for file_idx, file_path in enumerate(file_paths):
+    # Load dataset
+    df = pd.read_csv(file_path, parse_dates=["Time"])
+    df["Month"] = df["Time"].dt.month
+    df["Hour"] = df["Time"].dt.hour
+    
+    # Aggregate by hour
+    df_hourly = df.groupby(["Month", "Hour"])['grid active power'].mean().reset_index()
+    
+    # Normalize consumption active power
+    df_hourly['normalized grid active power'] = df_hourly['grid active power'] / df_hourly['grid active power'].max()
+    
+    # Plot each month
+    for month in df_hourly["Month"].unique():
+        subset = df_hourly[df_hourly["Month"] == month]
+        plt.plot(subset["Hour"], subset["normalized grid active power"], color=month_color_map[month], alpha=0.7, label=(months[month-1] if file_idx == 0 else ""))
+
+# Formatting the plot
+plt.xlabel("Hour of the Day")
+plt.ylabel("normalized grid active power")
+plt.title("Hourly normalized grid active power Grouped by Month")
+plt.legend(title="Month", loc="upper right")
+plt.grid(True)
+plt.savefig("normalized_grid_active_power_all_fenecon_dataset.jpg", format="jpg", dpi=300)
+plt.show()