136 lines
4.5 KiB
Python
136 lines
4.5 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import seaborn as sns
|
|
import matplotlib.pyplot as plt
|
|
import dataframe_image as dfi
|
|
# Load data
|
|
df = pd.read_csv("/home/shahin/Lab/Doktorarbeit/Barcelona/Data/Join_edssandsub.tsv", sep='\t')
|
|
|
|
# 1. Identify all GT and result columns
|
|
gt_columns = [col for col in df.columns if col.startswith('GT.')]
|
|
result_columns = [col for col in df.columns if col.startswith('result.')]
|
|
|
|
print("GT Columns found:", gt_columns)
|
|
print("Result Columns found:", result_columns)
|
|
|
|
# 2. Create proper mapping between GT and result columns
|
|
# Handle various naming conventions (spaces, underscores, etc.)
|
|
column_mapping = {}
|
|
|
|
for gt_col in gt_columns:
|
|
base_name = gt_col.replace('GT.', '')
|
|
|
|
# Clean the base name for matching - remove spaces, underscores, etc.
|
|
# Try different matching approaches
|
|
candidates = [
|
|
f'result.{base_name}', # Exact match
|
|
f'result.{base_name.replace(" ", "_")}', # With underscores
|
|
f'result.{base_name.replace("_", " ")}', # With spaces
|
|
f'result.{base_name.replace(" ", "")}', # No spaces
|
|
f'result.{base_name.replace("_", "")}' # No underscores
|
|
]
|
|
|
|
# Also try case-insensitive matching
|
|
candidates.append(f'result.{base_name.lower()}')
|
|
candidates.append(f'result.{base_name.upper()}')
|
|
|
|
# Try to find matching result column
|
|
matched = False
|
|
for candidate in candidates:
|
|
if candidate in result_columns:
|
|
column_mapping[gt_col] = candidate
|
|
matched = True
|
|
break
|
|
|
|
# If no exact match found, try partial matching
|
|
if not matched:
|
|
# Try to match by removing special characters and comparing
|
|
base_clean = ''.join(e for e in base_name if e.isalnum() or e in ['_', ' '])
|
|
for result_col in result_columns:
|
|
result_base = result_col.replace('result.', '')
|
|
result_clean = ''.join(e for e in result_base if e.isalnum() or e in ['_', ' '])
|
|
if base_clean.lower() == result_clean.lower():
|
|
column_mapping[gt_col] = result_col
|
|
matched = True
|
|
break
|
|
|
|
print("Column mapping:", column_mapping)
|
|
|
|
# 3. Faster, vectorized computation using the corrected mapping
|
|
data_list = []
|
|
|
|
for gt_col, result_col in column_mapping.items():
|
|
print(f"Processing {gt_col} vs {result_col}")
|
|
|
|
# Convert to numeric, forcing errors to NaN
|
|
s1 = pd.to_numeric(df[gt_col], errors='coerce').astype(float)
|
|
s2 = pd.to_numeric(df[result_col], errors='coerce').astype(float)
|
|
|
|
# Calculate matches (abs difference <= 0.5)
|
|
diff = np.abs(s1 - s2)
|
|
matches = (diff <= 0.5).sum()
|
|
|
|
# Determine the denominator (total valid comparisons)
|
|
valid_count = diff.notna().sum()
|
|
|
|
if valid_count > 0:
|
|
percentage = (matches / valid_count) * 100
|
|
else:
|
|
percentage = 0
|
|
|
|
# Extract clean base name for display
|
|
base_name = gt_col.replace('GT.', '')
|
|
|
|
data_list.append({
|
|
'GT': base_name,
|
|
'Match %': round(percentage, 1)
|
|
})
|
|
|
|
|
|
|
|
# 4. Prepare Data for Plotting
|
|
match_df = pd.DataFrame(data_list)
|
|
match_df = match_df.sort_values('Match %', ascending=False) # Sort for better visual flow
|
|
|
|
# 5. Create the Styled Gradient Table
|
|
def style_agreement_table(df):
|
|
return (df.style
|
|
.format({'Match %': '{:.1f}%'}) # Add % sign
|
|
.background_gradient(cmap='RdYlGn', subset=['Match %'], vmin=50, vmax=100) # Red to Green gradient
|
|
.set_properties(**{
|
|
'text-align': 'center',
|
|
'font-size': '12pt',
|
|
'border-collapse': 'collapse',
|
|
'border': '1px solid #D3D3D3'
|
|
})
|
|
.set_table_styles([
|
|
# Style the header
|
|
{'selector': 'th', 'props': [
|
|
('background-color', '#404040'),
|
|
('color', 'white'),
|
|
('font-weight', 'bold'),
|
|
('text-transform', 'uppercase'),
|
|
('padding', '10px')
|
|
]},
|
|
# Add hover effect
|
|
{'selector': 'tr:hover', 'props': [('background-color', '#f5f5f5')]}
|
|
])
|
|
.set_caption("EDSS Agreement Analysis: Ground Truth vs. Results (Tolerance ±0.5)")
|
|
)
|
|
|
|
# To display in a Jupyter Notebook:
|
|
styled_table = style_agreement_table(match_df)
|
|
styled_table
|
|
|
|
dfi.export(styled_table, "styled_table.png")
|
|
#styled_table.to_html("agreement_report.html")
|
|
# 6. Save as SVG
|
|
|
|
#plt.savefig("agreement_table.svg", format='svg', dpi=300, bbox_inches='tight')
|
|
#print("Successfully saved agreement_table.svg")
|
|
|
|
# Show plot if running in a GUI environment
|
|
plt.show()
|
|
|
|
|