# %% Explore import pandas as pd # Load the dataset file_path = '/home/shahin/Lab/Doktorarbeit/Barcelona/Data/MS_Briefe_400_with_unique_id_SHA3_explore_cleaned_unique.csv' df = pd.read_csv(file_path, sep=';') # Show basic information about the dataset print("Dataset shape:", df.shape) print("\nColumn names:") for col in df.columns: print(f" {col}") # Count unique patients unique_patients = df['unique_id'].nunique() print(f"\nNumber of unique patients: {unique_patients}") # Count how many times each patient appears patient_counts = df['unique_id'].value_counts() # Calculate average appearances per patient average_appearances = patient_counts.mean() # Show some statistics print(f"\nAverage number of times each patient appeared: {average_appearances:.2f}") print(f"\nMinimum appearances for any patient: {patient_counts.min()}") print(f"Maximum appearances for any patient: {patient_counts.max()}") # Show the first few patient counts print("\nFirst 10 patients and their appearance counts:") print(patient_counts.head(10)) # Show how many patients appear exactly once single_occurrence = (patient_counts == 1).sum() print(f"\nNumber of patients who appeared exactly once: {single_occurrence}") # Show how many patients appear more than once multiple_occurrence = (patient_counts > 1).sum() print(f"Number of patients who appeared more than once: {multiple_occurrence}") ## # %% EDSS Dist import pandas as pd import matplotlib.pyplot as plt import numpy as np # Assuming your data is loaded into a DataFrame called 'df' # If you need to load from file: df = pd.read_csv('/home/shahin/Lab/Doktorarbeit/Barcelona/Data/MS_Briefe_400_with_unique_id_SHA3_explore_cleaned_unique.csv', sep=';') # Create EDSS categories function with better error handling def categorize_edss(edss_value): # Handle NaN and empty values if pd.isna(edss_value) or edss_value == '' or edss_value is None: return 'No EDSS' # Convert to string and replace comma with dot edss_str = str(edss_value).strip() # Handle special cases if edss_str.lower() in ['unverändert', 'unchanged', 'n/a', 'na', 'none', 'null', '']: return 'Invalid' try: # Replace comma with dot for decimal numbers edss_str = edss_str.replace(',', '.') # Try to convert to float edss_float = float(edss_str) # Categorize based on value if 0 <= edss_float <= 1: return '0-1' elif 1 < edss_float <= 2: return '1-2' elif 2 < edss_float <= 3: return '2-3' elif 3 < edss_float <= 4: return '3-4' elif 4 < edss_float <= 5: return '4-5' elif 5 < edss_float <= 6: return '5-6' elif 6 < edss_float <= 7: return '6-7' elif 7 < edss_float <= 8: return '7-8' elif 8 < edss_float <= 9: return '8-9' elif 9 < edss_float <= 10: return '9-10' else: return 'Invalid' except (ValueError, TypeError): return 'Invalid' # Apply categorization df['EDSS_Category'] = df['EDSS'].apply(categorize_edss) # Count patients in each category edss_counts = df['EDSS_Category'].value_counts().sort_index() # Print the counts for reference print("Patient counts by EDSS category:") print(edss_counts) # Create the bar chart plt.figure(figsize=(12, 6)) bars = plt.bar(edss_counts.index, edss_counts.values, color='skyblue', edgecolor='navy', alpha=0.7) # Add value labels on top of bars for bar in bars: height = bar.get_height() plt.text(bar.get_x() + bar.get_width()/2., height, f'{int(height)}', ha='center', va='bottom') plt.xlabel('EDSS Score Categories') plt.ylabel('Number of Cases') plt.title('Distribution of Patients by EDSS Score Categories') plt.xticks(rotation=45) plt.grid(axis='y', alpha=0.3) plt.tight_layout() plt.show() ## # %% Pie Chart import matplotlib.pyplot as plt import pandas as pd # Your data data = { 'Visit': [9, 8, 7, 6, 5, 4, 3, 2, 1], 'patient_count': [2, 3, 3, 6, 13, 17, 28, 24, 32] } df = pd.DataFrame(data) # Create pie chart plt.figure(figsize=(10, 8)) # Define colors for better visualization colors = ['#ff9999', '#66b3ff', '#99ff99', '#ffcc99', '#ff99cc', '#c2c2f0', '#ffb3b3', '#99ffcc', '#ffccff'] # Create pie chart with custom labels showing both count and percentage labels = [f'{visit} Visits \n{count} patients\n({count/128*100:.1f}%)' for visit, count in zip(df['Visit'], df['patient_count'])] wedges, texts, autotexts = plt.pie(df['patient_count'], labels=labels, colors=colors, autopct='%1.1f%%', startangle=90, explode=[0.05] * len(df)) # Slightly separate slices # Add title plt.title('Patient Visit Frequency Distribution\nTotal Patients: 128\nTotal Cases: 396', fontsize=16, pad=20) # Ensure pie chart is circular plt.axis('equal') # Adjust layout to prevent legend cutoff plt.tight_layout() # Save as SVG (this will create a high-quality vector graphic) plt.savefig('patient_visit_frequency.svg', format='svg', bbox_inches='tight', dpi=300) # Also save as PNG for reference plt.savefig('patient_visit_frequency.png', format='png', bbox_inches='tight', dpi=300) # Show the chart plt.show() # Print summary statistics print(f"Total patients: {sum(df['patient_count'])}") print("\nVisit frequency breakdown:") for visit, count in zip(df['Visit'], df['patient_count']): percentage = (count / 128) * 100 print(f"{visit} Visits : {count} patients ({percentage:.1f}%)") print("\nFiles created:") print("- patient_visit_frequency.svg (SVG format)") print("- patient_visit_frequency.png (PNG format)") ## # %% Slope Chart import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import numpy as np # 1. Data Prep (Cleaning and filtering for patients with >1 visit) df['EDSS'] = pd.to_numeric(df['EDSS'].astype(str).str.replace(',', '.'), errors='coerce') df = df.dropna(subset=['unique_id', 'EDSS', 'MedDatum']).sort_values(['unique_id', 'MedDatum']) # Extract first and last first_last = df.groupby('unique_id').apply(lambda x: x.iloc[[0, -1]] if len(x) > 1 else None).reset_index(drop=True) first_last['Visit_Type'] = first_last.groupby('unique_id').cumcount().map({0: 'First Visit', 1: 'Last Visit'}) # 2. Set the style sns.set_style("white") plt.figure(figsize=(10, 8)) # Define sophisticated colors color_worsened = "#E67E22" # Muted Orange color_improved = "#2ECC71" # Muted Green color_stable = "#BDC3C7" # Soft Grey avg_color = "#2C3E50" # Deep Navy # 3. Plotting individual lines for pid in first_last['unique_id'].unique(): p_data = first_last[first_last['unique_id'] == pid] start, end = p_data.iloc[0]['EDSS'], p_data.iloc[1]['EDSS'] # Logic for color and linewidth if end > start: color, alpha, lw = color_worsened, 0.3, 1.2 elif end < start: color, alpha, lw = color_improved, 0.3, 1.2 else: color, alpha, lw = color_stable, 0.15, 0.8 plt.plot(p_data['Visit_Type'], p_data['EDSS'], color=color, alpha=alpha, linewidth=lw, marker='o', markersize=4, markerfacecolor='white') # 4. Add Background Distribution (Violin Plot) sns.violinplot(x='Visit_Type', y='EDSS', data=first_last, inner=None, color=".95", linewidth=0) # 5. Add the Population Mean (The "Hero" line) summary = first_last.groupby('Visit_Type')['EDSS'].mean().reindex(['First Visit', 'Last Visit']) plt.plot(summary.index, summary.values, color=avg_color, linewidth=4, marker='s', markersize=10, label='Average Population Trend', zorder=10) # 6. Annotate the Average values for i, val in enumerate(summary.values): plt.text(i, val + 0.2, f'{val:.2f}', color=avg_color, fontweight='bold', ha='center') # Aesthetics plt.title('Evolution of EDSS Scores: First vs. Last Clinical Visit', fontsize=16, pad=20, fontweight='bold') plt.ylabel('EDSS Score', fontsize=12) plt.xlabel('') plt.xticks(fontsize=12, fontweight='bold') plt.yticks(np.arange(0, 10.5, 1)) # Typical EDSS scale plt.ylim(-0.5, 10) # Remove chart junk sns.despine(left=True, bottom=True) plt.grid(axis='y', color='gray', linestyle='--', alpha=0.2) plt.legend(frameon=False, loc='upper center', bbox_to_anchor=(0.5, -0.05)) plt.tight_layout() plt.show() ##