shahin/EDSS-calc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

beautiful plot

Browse Source
This commit is contained in:
Shahin Ramezanzadeh
2026-01-19 01:26:14 +01:00
parent 8f34f06578
commit a1a8abfb8e
2 changed files with 199 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
Data/show_plots.py
View File

@@ -407,7 +407,7 @@ 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')
@@ -491,32 +491,76 @@ for gt_col, result_col in column_mapping.items():
'Match %': round(percentage, 1)
})
# 4. Prepare Data for Plotting
# 4. Prepare Data
match_df = pd.DataFrame(data_list)
# Clean up labels: Replace underscores with spaces and capitalize
match_df['GT'] = match_df['GT'].str.replace('_', ' ').str.title()
match_df = match_df.sort_values('Match %', ascending=False)
# Handle case where no matches were found
if len(match_df) == 0:
print("No valid column pairs found for comparison")
exit()
# 5. Create a "Beautiful" Table using Seaborn Heatmap
def create_luxury_table(df, output_file="edss_agreement.png"):
# Set the aesthetic style
sns.set_theme(style="white", font="sans-serif")
# 5. Create the Plot
plt.figure(figsize=(10, 8))
sns.set_theme(style="white")
# Prepare data for heatmap
plot_data = df.set_index('GT')[['Match %']]
# Create heatmap
ax = sns.heatmap(
match_df.set_index('GT')[['Match %']], # Just the percentage column
annot=True, # Show the numbers in the boxes
fmt=".1f", # Format to 1 decimal place
cmap="YlGnBu", # Yellow-Green-Blue color palette
cbar_kws={'label': 'Agreement (%)'},
linewidths=.5
# Initialize the figure
# Height is dynamic based on number of rows
fig, ax = plt.subplots(figsize=(8, len(df) * 0.6))
# Create a custom diverging color map (Deep Red -> Mustard -> Emerald)
# This looks more professional than standard 'RdYlGn'
cmap = sns.diverging_palette(15, 135, s=80, l=55, as_cmap=True)
# Draw the heatmap
sns.heatmap(
plot_data,
annot=True,
fmt=".1f",
cmap=cmap,
center=85, # Centers the color transition
vmin=50, vmax=100, # Range of the gradient
linewidths=2,
linecolor='white',
cbar=False, # Remove color bar for a "table" look
annot_kws={"size": 14, "weight": "bold", "family": "sans-serif"}
)
plt.title('Agreement Percentage (Tolerance ±0.5)', pad=20)
plt.tight_layout()
# Styling the Axes (Turning the heatmap into a table)
ax.set_xlabel("")
ax.set_ylabel("")
ax.xaxis.tick_top() # Move "Match %" label to top
ax.set_xticklabels(['Agreement (%)'], fontsize=14, fontweight='bold', color='#2c3e50')
ax.tick_params(axis='y', labelsize=12, labelcolor='#2c3e50', length=0)
# Add a thin border around the plot
for _, spine in ax.spines.items():
spine.set_visible(True)
spine.set_color('#ecf0f1')
plt.title('EDSS Subcategory Consistency Analysis', fontsize=16, pad=40, fontweight='bold', color='#2c3e50')
# Add a subtle footer
plt.figtext(0.5, 0.02, "Tolerance: ±0.5 points | N = [Total Samples]",
wrap=True, horizontalalignment='center', fontsize=10, color='gray', style='italic')
# Save with high resolution
plt.tight_layout()
plt.savefig(output_file, dpi=300, bbox_inches='tight')
print(f"Beautiful table saved as {output_file}")
# Execute
create_luxury_table(match_df)
# Run the function
save_styled_table(match_df)
# 6. Save as SVG
#plt.savefig("agreement_table.svg", format='svg', dpi=300, bbox_inches='tight')
#print("Successfully saved agreement_table.svg")

135
Data/style2.py Normal file
View File

@@ -0,0 +1,135 @@
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()