Spaces:
Running
Running
File size: 6,011 Bytes
b308ad4 ff25539 b308ad4 2534fa7 ff25539 b308ad4 3671dd0 b308ad4 3671dd0 b308ad4 dc454dd b308ad4 3671dd0 b308ad4 3671dd0 b308ad4 3671dd0 b308ad4 3671dd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
import gradio as gr
import pandas as pd
import re
import os
import json
import yaml
import matplotlib.pyplot as plt
import seaborn as sns
import plotnine as p9
import sys
script_dir = os.path.dirname(os.path.abspath(__file__))
sys.path.append('..')
sys.path.append('.')
from about import *
global data_component, filter_component
def get_baseline_df(selected_methods, selected_metrics):
df = pd.read_csv(CSV_RESULT_PATH)
present_columns = ["method_name"] + selected_metrics
df = df[df['method_name'].isin(selected_methods)][present_columns]
return df
def get_method_color(method):
return color_dict.get(method, 'black') # If method is not in color_dict, use black
def set_colors_and_marks_for_representation_groups(ax):
for label in ax.get_xticklabels():
text = label.get_text()
color = group_color_dict.get(text, 'black') # Default to black if label not in dict
label.set_color(color)
label.set_fontweight('bold')
# Add a caret symbol to specific labels
if text in {'MUT2VEC', 'PFAM', 'GENE2VEC', 'BERT-PFAM'}:
label.set_text(f"^ {text}")
def benchmark_plot(benchmark_type, methods_selected, x_metric, y_metric):
if benchmark_type == 'flexible':
# Use general visualizer logic
return general_visualizer_plot(methods_selected, x_metric=x_metric, y_metric=y_metric)
elif benchmark_type == 'similarity':
title = f"{x_metric} vs {y_metric}"
return draw_scatter_plot_similarity(methods_selected, x_metric, y_metric, title)
elif benchmark_type == 'Benchmark 3':
return benchmark_3_plot(x_metric, y_metric)
elif benchmark_type == 'Benchmark 4':
return benchmark_4_plot(x_metric, y_metric)
else:
return "Invalid benchmark type selected."
def general_visualizer(methods_selected, x_metric, y_metric):
df = pd.read_csv(CSV_RESULT_PATH)
filtered_df = df[df['method_name'].isin(methods_selected)]
# Create a Seaborn lineplot with method as hue
plt.figure(figsize=(10, 8)) # Increase figure size
sns.lineplot(
data=filtered_df,
x=x_metric,
y=y_metric,
hue="method_name", # Different colors for different methods
marker="o", # Add markers to the line plot
)
# Add labels and title
plt.xlabel(x_metric)
plt.ylabel(y_metric)
plt.title(f'{y_metric} vs {x_metric} for selected methods')
plt.grid(True)
# Save the plot to display it in Gradio
plot_path = "plot.png"
plt.savefig(plot_path)
plt.close()
return plot_path
def draw_scatter_plot_similarity(methods_selected, x_metric, y_metric, title):
df = pd.read_csv(CSV_RESULT_PATH)
# Filter the dataframe based on selected methods
filtered_df = df[df['method_name'].isin(methods_selected)]
def get_method_color(method):
return color_dict.get(method.upper(), 'black')
# Add a new column to the dataframe for the color
filtered_df['color'] = filtered_df['method_name'].apply(get_method_color)
adjust_text_dict = {
'expand_text': (1.15, 1.4), 'expand_points': (1.15, 1.25), 'expand_objects': (1.05, 1.5),
'expand_align': (1.05, 1.2), 'autoalign': 'xy', 'va': 'center', 'ha': 'center',
'force_text': (.0, 1.), 'force_objects': (.0, 1.),
'lim': 500000, 'precision': 1., 'avoid_points': True, 'avoid_text': True
}
# Create the scatter plot using plotnine (ggplot)
g = (p9.ggplot(data=filtered_df,
mapping=p9.aes(x=x_metric, # Use the selected x_metric
y=y_metric, # Use the selected y_metric
color='color', # Use the dynamically generated color
label='method_name')) # Label each point by the method name
+ p9.geom_point(size=3) # Add points with no jitter, set point size
+ p9.geom_text(nudge_y=0.02, size=8) # Add method names as labels, nudge slightly above the points
+ p9.labs(title=title, x=f"{x_metric}", y=f"{y_metric}") # Dynamic labels for X and Y axes
+ p9.scale_color_identity() # Use colors directly from the dataframe
+ p9.theme(legend_position='none',
figure_size=(8, 8), # Set figure size
axis_text=p9.element_text(size=10),
axis_title_x=p9.element_text(size=12),
axis_title_y=p9.element_text(size=12))
)
# Save the plot as an image
save_path = "./plot_images" # Ensure this folder exists or adjust the path
os.makedirs(save_path, exist_ok=True) # Create directory if it doesn't exist
filename = os.path.join(save_path, title.replace(" ", "_") + "_Similarity_Scatter.png")
g.save(filename=filename, dpi=400)
return filename
def visualize_aspect_metric_clustermap(file_path, aspect, metric, method_names):
# Load data
df = pd.read_csv(file_path)
# Filter for selected methods
df = df[df['Method'].isin(method_names)]
# Filter columns for specified aspect and metric
columns_to_plot = [col for col in df.columns if col.startswith(f"{aspect}_") and col.endswith(f"_{metric}")]
df = df[['Method'] + columns_to_plot]
df.set_index('Method', inplace=True)
# Create clustermap
g = sns.clustermap(df, annot=True, cmap="YlGnBu", row_cluster=False, col_cluster=False, figsize=(15, 15))
# Get heatmap axis and customize labels
ax = g.ax_heatmap
ax.set_xlabel("")
ax.set_ylabel("")
# Apply color and caret adjustments to x-axis labels
set_colors_and_marks_for_representation_groups(ax)
# Save the plot as an image
os.makedirs(save_path, exist_ok=True) # Create directory if it doesn't exist
filename = os.path.join(save_path, f"{aspect}_{metric}_heatmap.png")
plt.savefig(filename, dpi=400, bbox_inches='tight')
plt.close() # Close the plot to free memory
return filename |