Create app.py

app.py

@@ -0,0 +1,141 @@
+import os, pathlib, numpy as np, pandas as pd, faiss, gradio as gr
+from huggingface_hub import hf_hub_download
+from sentence_transformers import SentenceTransformer
+
+# =========================
+# CONFIG — EDIT IF NEEDED
+# =========================
+HF_DATASET_REPO = "miazaitman/CheatClean"
+HF_DATASET_FILE = "CheatClean Data set.csv"  # keep spaces exactly as in the file name
+
+DATA_DIR = pathlib.Path("./data"); DATA_DIR.mkdir(exist_ok=True)
+CACHE_DIR = pathlib.Path("./cache"); CACHE_DIR.mkdir(exist_ok=True)
+DATA_LOCAL = DATA_DIR / HF_DATASET_FILE
+EMBED_MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2"
+
+# -------------------------
+# Load dataset from HF Hub
+# -------------------------
+def load_dataset():
+    if not DATA_LOCAL.exists():
+        hf_hub_download(
+            repo_id=HF_DATASET_REPO,
+            filename=HF_DATASET_FILE,
+            local_dir=str(DATA_DIR),
+            local_dir_use_symlinks=False
+        )
+    df = pd.read_csv(DATA_LOCAL)
+
+    # Expected columns from CheatClean dataset
+    needed = [
+        "Unhealthy_Food",
+        "Alt1_Name", "Alt1_Description", "Alt1_Estimated_Calorie_Delta_kcal", "Alt1_Macro_Delta", "Alt1_Tip",
+        "Alt2_Name", "Alt2_Description", "Alt2_Estimated_Calorie_Delta_kcal", "Alt2_Macro_Delta", "Alt2_Tip",
+        "Alt3_Name", "Alt3_Description", "Alt3_Estimated_Calorie_Delta_kcal", "Alt3_Macro_Delta", "Alt3_Tip"
+    ]
+    missing = [c for c in needed if c not in df.columns]
+    if missing:
+        raise ValueError(f"Missing columns in dataset: {missing}")
+
+    df = df.dropna(subset=["Unhealthy_Food"]).reset_index(drop=True)
+    return df
+
+# -------------------------
+# Build FAISS index
+# -------------------------
+def build_index(texts):
+    model = SentenceTransformer(EMBED_MODEL_NAME)
+    embs = model.encode(texts, convert_to_numpy=True, show_progress_bar=True)
+    faiss.normalize_L2(embs)
+    index = faiss.IndexFlatIP(embs.shape[1])
+    index.add(embs)
+    return model, index
+
+# -------------------------
+# Find closest match & return its 3 alternatives
+# -------------------------
+def find_row(user_food, topk_rows=1):
+    q = (user_food or "").strip()
+    if not q:
+        return []
+    q_emb = model.encode([q], convert_to_numpy=True)
+    faiss.normalize_L2(q_emb)
+    D, I = index.search(q_emb, topk_rows)
+    return I[0].tolist()
+
+def to_three_alternatives(row):
+    return [
+        {
+            "Rank": 1,
+            "Healthier Alternative": row["Alt1_Name"],
+            "Description": row["Alt1_Description"],
+            "Calorie/Nutrient Difference": f'{row["Alt1_Estimated_Calorie_Delta_kcal"]} kcal; {row["Alt1_Macro_Delta"]}',
+            "Tip": row["Alt1_Tip"],
+        },
+        {
+            "Rank": 2,
+            "Healthier Alternative": row["Alt2_Name"],
+            "Description": row["Alt2_Description"],
+            "Calorie/Nutrient Difference": f'{row["Alt2_Estimated_Calorie_Delta_kcal"]} kcal; {row["Alt2_Macro_Delta"]}',
+            "Tip": row["Alt2_Tip"],
+        },
+        {
+            "Rank": 3,
+            "Healthier Alternative": row["Alt3_Name"],
+            "Description": row["Alt3_Description"],
+            "Calorie/Nutrient Difference": f'{row["Alt3_Estimated_Calorie_Delta_kcal"]} kcal; {row["Alt3_Macro_Delta"]}',
+            "Tip": row["Alt3_Tip"],
+        },
+    ]
+
+# -------------------------
+# UI logic
+# -------------------------
+def search_ui(user_food):
+    idxs = find_row(user_food, 1)
+    if not idxs:
+        return f"**You entered:** _{user_food}_\n\nNo matches found.", None
+    row = df.iloc[idxs[0]]
+    echoed = f"**You entered:** _{user_food}_"
+    table = pd.DataFrame(to_three_alternatives(row), columns=[
+        "Rank", "Healthier Alternative", "Description", "Calorie/Nutrient Difference", "Tip"
+    ])
+    return echoed, table
+
+def build_interface():
+    examples = [
+        ["Hamburger"],
+        ["Cheeseburger"],
+        ["Pepperoni Pizza"],
+        ["Fried Chicken Sandwich"],
+        ["Nachos"],
+        ["Mac and Cheese"],
+    ]
+    with gr.Blocks(title="Healthy Food Alternatives") as demo:
+        gr.Markdown("# 🥗 Healthy Food Alternatives\nType a food you like to see healthier options.")
+        with gr.Row():
+            with gr.Column(scale=1):
+                inp = gr.Textbox(label="Enter a food you like", placeholder="e.g., Hamburger")
+                btn = gr.Button("Find Healthier Alternatives", variant="primary")
+                gr.Examples(examples=examples, inputs=inp, label="Try one")
+            with gr.Column(scale=2):
+                echoed = gr.Markdown()
+                table = gr.Dataframe(
+                    headers=["Rank", "Healthier Alternative", "Description", "Calorie/Nutrient Difference", "Tip"],
+                    row_count=(3, "fixed"),
+                    wrap=True
+                )
+        btn.click(search_ui, inputs=inp, outputs=[echoed, table])
+        inp.submit(search_ui, inputs=inp, outputs=[echoed, table])
+    return demo
+
+# -------------------------
+# Boot
+# -------------------------
+df = load_dataset()
+model, index = build_index(df["Unhealthy_Food"].astype(str).tolist())
+app = build_interface()
+
+if __name__ == "__main__":
+    app.launch()
+