Update app.py

app.py

@@ -1,7 +1,4 @@
-import os
-import zipfile
-import tempfile
-import requests
+import os, zipfile, tempfile, requests, io
 import numpy as np
 import pandas as pd
 from PIL import Image
@@ -11,9 +8,7 @@ from torchvision import transforms
 from torchvision.models import resnet50, ResNet50_Weights
 from sklearn.cluster import MiniBatchKMeans
 import matplotlib.pyplot as plt
-import io
 from datetime import datetime
-
 import gradio as gr
 from deepface import DeepFace
 import cv2
@@ -31,7 +26,6 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 weights = ResNet50_Weights.DEFAULT
 model = resnet50(weights=weights).to(device)
 model.eval()
-
 transform = transforms.Compose([
     transforms.Resize(256),
     transforms.CenterCrop(224),
@@ -50,7 +44,7 @@ BASIC_COLORS = {
 
 def closest_basic_color(rgb):
     r,g,b = rgb
-    min_dist = float("inf"); closest_color = None
+    min_dist, closest_color = float("inf"), None
     for name,(cr,cg,cb) in BASIC_COLORS.items():
         dist = (r-cr)**2 + (g-cg)**2 + (b-cb)**2
         if dist < min_dist:
@@ -73,7 +67,7 @@ def get_dominant_color(image,num_colors=5):
 # ---------------------------
 def classify_zip_and_analyze_color(zip_file):
     results = []
-    images_list = []  # list of (image, label) for gallery
+    images_list = []
     zip_name = os.path.splitext(os.path.basename(zip_file.name))[0]
     date_str = datetime.now().strftime("%Y%m%d")
 
@@ -90,6 +84,7 @@ def classify_zip_and_analyze_color(zip_file):
                 except:
                     continue
 
+                # Classification
                 input_tensor = transform(image).unsqueeze(0).to(device)
                 with torch.no_grad():
                     output = model(input_tensor)
@@ -100,6 +95,7 @@ def classify_zip_and_analyze_color(zip_file):
                 rgb, hex_color = get_dominant_color(image)
                 basic_color = closest_basic_color(rgb)
 
+                # Face analysis
                 faces_data = []
                 try:
                     img_cv2 = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
@@ -112,13 +108,16 @@ def classify_zip_and_analyze_color(zip_file):
                 except:
                     faces_data=[]
 
+                # Convert faces data to readable string
+                faces_str = "; ".join([f"Age: {face['age']}, Gender: {'Homme' if face['gender']=='Man' else 'Femme'}, Emotion: {face['emotion']}" for face in faces_data])
+
                 results.append((
                     fname,
                     ", ".join([p[0] for p in preds]),
                     ", ".join([p[1] for p in preds]),
                     hex_color,
                     basic_color,
-                    faces_data
+                    faces_str
                 ))
 
     df = pd.DataFrame(results, columns=["Filename","Top 3 Predictions","Confidence","Dominant Color","Basic Color","Face Info"])
@@ -131,8 +130,7 @@ def classify_zip_and_analyze_color(zip_file):
     fig1, ax1 = plt.subplots()
     color_counts = df["Basic Color"].value_counts()
     ax1.bar(color_counts.index, color_counts.values, color="skyblue")
-    ax1.set_title("Basic Color Frequency")
-    ax1.set_ylabel("Count")
+    ax1.set_title("Basic Color Frequency"); ax1.set_ylabel("Count")
     buf1 = io.BytesIO(); plt.savefig(buf1, format="png"); plt.close(fig1); buf1.seek(0); plot1_img = Image.open(buf1)
 
     fig2, ax2 = plt.subplots()
@@ -140,35 +138,33 @@ def classify_zip_and_analyze_color(zip_file):
     for p in df["Top 3 Predictions"]: preds_flat.extend(p.split(", "))
     pred_counts = pd.Series(preds_flat).value_counts().head(20)
     ax2.barh(pred_counts.index[::-1], pred_counts.values[::-1], color="salmon")
-    ax2.set_title("Top Prediction Distribution")
-    ax2.set_xlabel("Count")
+    ax2.set_title("Top Prediction Distribution"); ax2.set_xlabel("Count")
     buf2 = io.BytesIO(); plt.savefig(buf2, format="png", bbox_inches="tight"); plt.close(fig2); buf2.seek(0); plot2_img = Image.open(buf2)
 
+    # Gender and age
     ages_male, ages_female = [], []
     gender_confidence = {"Homme":0, "Femme":0}
     for face_list in df["Face Info"]:
-        for face in face_list:
-            age = face["age"]
-            gender_dict = face["gender"]
-            gender = max(gender_dict, key=gender_dict.get)
-            conf = float(gender_dict[gender])/100
-            weight = min(conf,0.9)
-            gender_trans = "Homme" if gender=="Man" else "Femme"
-            gender_confidence[gender_trans] += weight
-            if gender_trans=="Homme": ages_male.append(age)
+        if face_list.strip()=="":
+            continue
+        for face_str in face_list.split("; "):
+            parts = face_str.split(", ")
+            age = int(parts[0].split(": ")[1])
+            gender = parts[1].split(": ")[1]
+            conf = 0.9  # approximation for histogram
+            gender_confidence[gender] += conf
+            if gender=="Homme": ages_male.append(age)
             else: ages_female.append(age)
 
     fig3, ax3 = plt.subplots()
     ax3.bar(gender_confidence.keys(), gender_confidence.values(), color=["lightblue","pink"])
-    ax3.set_title("Gender Distribution (Weighted ≤90%)")
-    ax3.set_ylabel("Sum of Confidence")
+    ax3.set_title("Gender Distribution"); ax3.set_ylabel("Sum of Confidence")
     buf3 = io.BytesIO(); plt.savefig(buf3, format="png"); plt.close(fig3); buf3.seek(0); plot3_img = Image.open(buf3)
 
     fig4, ax4 = plt.subplots()
     bins = range(0,101,5)
     ax4.hist([ages_male, ages_female], bins=bins, color=["lightblue","pink"], label=["Homme","Femme"], edgecolor="black")
-    ax4.set_title("Age Distribution by Gender")
-    ax4.set_xlabel("Age"); ax4.set_ylabel("Count"); ax4.legend()
+    ax4.set_title("Age Distribution by Gender"); ax4.set_xlabel("Age"); ax4.set_ylabel("Count"); ax4.legend()
     buf4 = io.BytesIO(); plt.savefig(buf4, format="png"); plt.close(fig4); buf4.seek(0); plot4_img = Image.open(buf4)
 
     return df, images_list, out_xlsx, plot1_img, plot2_img, plot3_img, plot4_img