Add Gradio classifier app (app.py, requirements.txt, README)

README.md

@@ -1,10 +1,39 @@
 ---
-title: Sitasector
-emoji: 🖼️
-colorFrom: yellow
-colorTo: red
-sdk: static
+title: Sita Sector Classifier
+emoji: 🌍
+colorFrom: green
+colorTo: green
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Sita Sector Classifier
+
+Gradio web UI for the fine-tuned DistilBERT sector classifier built by MC Studio (Christine Matinde and Stacey Nduta) for the IBM x MC Studio Program.
+
+## What it does
+
+Paste a company description and it predicts the most likely Sita Sector industry, with confidence.
+
+## Model
+
+- Model: `mcsqstudio/africa-sector-classifier` (DistilBERT fine-tuned on 7 sectors)
+- Dataset: [mcsqstudio/africa-startup-directory](https://huggingface.co/datasets/mcsqstudio/africa-startup-directory)
+
+## Sectors
+
+| Code | Sector |
+| ---- | ------ |
+| ATX | Agritech |
+| ETX | Edtech |
+| HTX | Healthtech |
+| FTX | Fintech |
+| REC | Retail & E-commerce |
+| ERG | Energy |
+| MFG | Manufacturing |
+
+## Note
+
+This Space activates the model lazily on first use. If it reports that the model is not ready, run `Sita_Sector_Model_v2_transformers.ipynb` in Colab to fine-tune and push the model, then click Classify again.

app.py

@@ -0,0 +1,90 @@
+import pandas as pd
+import gradio as gr
+from transformers import pipeline
+
+MODEL_ID = "mcsqstudio/africa-sector-classifier"
+
+SECTOR_NAMES = {
+    "ATX": "Agritech",
+    "ETX": "Edtech",
+    "HTX": "Healthtech",
+    "FTX": "Fintech",
+    "REC": "Retail & E-commerce",
+    "ERG": "Energy",
+    "MFG": "Manufacturing",
+    "XSC": "Cross-sector",
+}
+
+_pipe = None
+_model_error = None
+
+
+def get_pipe():
+    global _pipe, _model_error
+    if _pipe is None:
+        try:
+            _pipe = pipeline("text-classification", model=MODEL_ID, truncation=True)
+            _model_error = None
+        except Exception as exc:
+            _model_error = str(exc)
+    return _pipe
+
+
+def classify(text):
+    if not text or not text.strip():
+        return pd.DataFrame(), "Please enter a company description."
+    pipe = get_pipe()
+    if pipe is None:
+        return pd.DataFrame(), (
+            "Model not ready yet. Run **Sita_Sector_Model_v2_transformers.ipynb** "
+            "in Colab to fine-tune and push `mcsqstudio/africa-sector-classifier` "
+            "to Hugging Face, then click Classify again.\n\n"
+            f"Detail: {_model_error}"
+        )
+    results = pipe(text.strip()[:2000])
+    rows = [
+        {
+            "Sector": r["label"],
+            "Sector name": SECTOR_NAMES.get(r["label"], ""),
+            "Confidence": round(r["score"], 4),
+        }
+        for r in results
+    ]
+    df = pd.DataFrame(rows)
+    top = rows[0]
+    headline = (
+        f"**{top['Sector']} - {SECTOR_NAMES.get(top['Sector'], '')}** "
+        f"({top['Confidence']:.1%} confidence)"
+    )
+    return df, headline
+
+
+EXAMPLES = [
+    "Mobile payment platform enabling small businesses to accept card payments in Nairobi",
+    "Solar-powered microgrids bringing affordable electricity to rural communities in Uganda",
+    "Online marketplace connecting farmers directly to buyers and aggregating harvest data",
+    "AI tutoring app that personalizes math lessons for secondary school students in Nigeria",
+    "Telemedicine service offering remote consultations with licensed doctors in Kenya",
+]
+
+with gr.Blocks(title="Sita Sector Classifier") as demo:
+    gr.Markdown(
+        "# Sita Sector Classifier\n"
+        "Classifies an African startup description into one of seven Sita Sector industries. "
+        "Fine-tuned DistilBERT on the "
+        "[Africa Startup Directory](https://huggingface.co/datasets/mcsqstudio/africa-startup-directory).\n\n"
+        "**Sectors:** ATX Agritech - ETX Edtech - HTX Healthtech - FTX Fintech - "
+        "REC Retail & E-commerce - ERG Energy - MFG Manufacturing"
+    )
+    txt = gr.Textbox(label="Company description", lines=4)
+    btn = gr.Button("Classify", variant="primary")
+    headline = gr.Markdown()
+    out = gr.Dataframe(
+        headers=["Sector", "Sector name", "Confidence"],
+        datatype=["str", "str", "number"],
+        interactive=False,
+    )
+    btn.click(classify, inputs=txt, outputs=[out, headline])
+    gr.Examples(examples=EXAMPLES, inputs=txt)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=4.36
+transformers>=4.44
+torch>=2.1
+pandas>=2.0