import pandas as pd import matplotlib.pyplot as plt import seaborn as sns from datetime import datetime import numpy as np # Set style for better-looking plots plt.style.use('default') sns.set_palette("husl") def load_and_plot_data(): """Load the CSV data and create comprehensive plots""" # Load the data try: df = pd.read_csv('data/08072025_GliderFET001_noniso.csv') print(f"Data loaded successfully! Shape: {df.shape}") print(f"Columns: {list(df.columns)}") print(f"Data range: {df['DateTime'].min()} to {df['DateTime'].max()}") print(f"Number of measurements: {len(df)}") except FileNotFoundError: print("Error: Could not find the CSV file. Please check the path.") return except Exception as e: print(f"Error loading data: {e}") return # Convert DateTime to datetime object df['DateTime'] = pd.to_datetime(df['DateTime']) # Create a comprehensive figure with subplots fig, axes = plt.subplots(3, 2, figsize=(15, 12)) fig.suptitle('GliderFET001 Non-ISO Sensor Data Analysis', fontsize=16, fontweight='bold') # Plot 1: Temperature over time axes[0, 0].plot(df['DateTime'], df['Temperature'], 'b-', linewidth=1, alpha=0.8) axes[0, 0].set_title('Temperature Over Time', fontweight='bold') axes[0, 0].set_ylabel('Temperature (°C)') axes[0, 0].grid(True, alpha=0.3) axes[0, 0].tick_params(axis='x', rotation=45) # Plot 2: Salinity over time axes[0, 1].plot(df['DateTime'], df['Salinity'], 'g-', linewidth=1, alpha=0.8) axes[0, 1].set_title('Salinity Over Time', fontweight='bold') axes[0, 1].set_ylabel('Salinity (PSU)') axes[0, 1].grid(True, alpha=0.3) axes[0, 1].tick_params(axis='x', rotation=45) # Plot 3: Vrse (Reference Electrode Voltage) over time axes[1, 0].plot(df['DateTime'], df['Vrse'], 'r-', linewidth=1, alpha=0.8) axes[1, 0].set_title('Vrse (Reference Electrode Voltage) Over Time', fontweight='bold') axes[1, 0].set_ylabel('Vrse (V)') axes[1, 0].grid(True, alpha=0.3) axes[1, 0].tick_params(axis='x', rotation=45) # Plot 4: Vk (Working Electrode Voltage) over time axes[1, 1].plot(df['DateTime'], df['Vk'], 'm-', linewidth=1, alpha=0.8) axes[1, 1].set_title('Vk (Working Electrode Voltage) Over Time', fontweight='bold') axes[1, 1].set_ylabel('Vk (V)') axes[1, 1].grid(True, alpha=0.3) axes[1, 1].tick_params(axis='x', rotation=45) # Plot 5: Current measurements (Ik and Ib) over time with dual y-axes ax5 = axes[2, 0] ax5_twin = ax5.twinx() # Plot Ik on left y-axis line1 = ax5.plot(df['DateTime'], df['Ik'], 'c-', linewidth=1, alpha=0.8, label='Ik (Working Current)') ax5.set_ylabel('Ik (Working Current) - nA', color='c') ax5.tick_params(axis='y', labelcolor='c') # Plot Ib on right y-axis line2 = ax5_twin.plot(df['DateTime'], df['Ib'], 'orange', linewidth=1, alpha=0.8, label='Ib (Bias Current)') ax5_twin.set_ylabel('Ib (Bias Current) - nA', color='orange') ax5_twin.tick_params(axis='y', labelcolor='orange') ax5.set_title('Current Measurements Over Time', fontweight='bold') ax5.grid(True, alpha=0.3) ax5.tick_params(axis='x', rotation=45) # Create combined legend lines = line1 + line2 labels = [l.get_label() for l in lines] ax5.legend(lines, labels, loc='upper left') # Plot 6: VbiasPos (Bias Voltage) over time axes[2, 1].plot(df['DateTime'], df['VbiasPos'], 'purple', linewidth=1, alpha=0.8) axes[2, 1].set_title('VbiasPos (Bias Voltage) Over Time', fontweight='bold') axes[2, 1].set_ylabel('VbiasPos (V)') axes[2, 1].grid(True, alpha=0.3) axes[2, 1].tick_params(axis='x', rotation=45) # Adjust layout plt.tight_layout() # Save the plot plt.savefig('gliderfet_data_analysis.png', dpi=300, bbox_inches='tight') print("Plot saved as 'gliderfet_data_analysis.png'") # Show the plot plt.show() # Create additional analysis plots create_additional_plots(df) def create_additional_plots(df): """Create additional analysis plots""" # Create a new figure for correlation and distribution analysis fig2, axes2 = plt.subplots(2, 2, figsize=(15, 10)) fig2.suptitle('Additional Data Analysis', fontsize=16, fontweight='bold') # Plot 1: Temperature vs Salinity scatter plot axes2[0, 0].scatter(df['Temperature'], df['Salinity'], alpha=0.6, s=20) axes2[0, 0].set_xlabel('Temperature (°C)') axes2[0, 0].set_ylabel('Salinity (PSU)') axes2[0, 0].set_title('Temperature vs Salinity', fontweight='bold') axes2[0, 0].grid(True, alpha=0.3) # Plot 2: Vrse vs Vk scatter plot axes2[0, 1].scatter(df['Vrse'], df['Vk'], alpha=0.6, s=20) axes2[0, 1].set_xlabel('Vrse (V)') axes2[0, 1].set_ylabel('Vk (V)') axes2[0, 1].set_title('Vrse vs Vk', fontweight='bold') axes2[0, 1].grid(True, alpha=0.3) # Plot 3: Temperature distribution histogram axes2[1, 0].hist(df['Temperature'], bins=30, alpha=0.7, color='skyblue', edgecolor='black') axes2[1, 0].set_xlabel('Temperature (°C)') axes2[1, 0].set_ylabel('Frequency') axes2[1, 0].set_title('Temperature Distribution', fontweight='bold') axes2[1, 0].grid(True, alpha=0.3) # Plot 4: Salinity distribution histogram axes2[1, 1].hist(df['Salinity'], bins=30, alpha=0.7, color='lightgreen', edgecolor='black') axes2[1, 1].set_xlabel('Salinity (PSU)') axes2[1, 1].set_ylabel('Frequency') axes2[1, 1].set_title('Salinity Distribution', fontweight='bold') axes2[1, 1].grid(True, alpha=0.3) plt.tight_layout() # Save the additional plots plt.savefig('gliderfet_additional_analysis.png', dpi=300, bbox_inches='tight') print("Additional plots saved as 'gliderfet_additional_analysis.png'") # Show the additional plots plt.show() # Print summary statistics print_summary_statistics(df) def print_summary_statistics(df): """Print summary statistics for the data""" print("\n" + "="*60) print("SUMMARY STATISTICS") print("="*60) # Basic statistics for numerical columns numerical_cols = ['Temperature', 'Salinity', 'VbiasPos', 'Vrse', 'Vk', 'Ik', 'Ib'] for col in numerical_cols: if col in df.columns: print(f"\n{col}:") print(f" Mean: {df[col].mean():.6f}") print(f" Std: {df[col].std():.6f}") print(f" Min: {df[col].min():.6f}") print(f" Max: {df[col].max():.6f}") # Time range information print(f"\nTime Range:") print(f" Start: {df['DateTime'].min()}") print(f" End: {df['DateTime'].max()}") print(f" Duration: {df['DateTime'].max() - df['DateTime'].min()}") # Data quality information print(f"\nData Quality:") print(f" Total measurements: {len(df)}") print(f" Missing values: {df.isnull().sum().sum()}") # Calculate measurement frequency time_diff = df['DateTime'].diff().dropna() avg_interval = time_diff.mean() print(f" Average measurement interval: {avg_interval}") if __name__ == "__main__": # Run the main analysis load_and_plot_data()