Upload with huggingface_hub

README.md

@@ -1,12 +1,11 @@
+
 ---
-title: Interpretation Component Main
-emoji: 😻
-colorFrom: yellow
-colorTo: gray
+title: interpretation_component_main 
+emoji: 🔥
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
 sdk_version: 3.16.2
-app_file: app.py
+app_file: run.py
 pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,4 @@
+shap
+transformers
+torch
+https://gradio-main-build.s3.amazonaws.com/9a259cb8d0d002b445c4a36e0b60821d8b1ca052/gradio-3.16.2-py3-none-any.whl

run.ipynb

@@ -0,0 +1 @@
+{"cells": [{"cell_type": "markdown", "id": 302934307671667531413257853548643485645, "metadata": {}, "source": ["# Gradio Demo: interpretation_component"]}, {"cell_type": "code", "execution_count": null, "id": 272996653310673477252411125948039410165, "metadata": {}, "outputs": [], "source": ["!pip install -q gradio shap transformers torch"]}, {"cell_type": "code", "execution_count": null, "id": 288918539441861185822528903084949547379, "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import shap\n", "from transformers import pipeline\n", "\n", "\n", "sentiment_classifier = pipeline(\"text-classification\", return_all_scores=True)\n", "\n", "def interpretation_function(text):\n", "    explainer = shap.Explainer(sentiment_classifier)\n", "    shap_values = explainer([text])\n", "    scores = list(zip(shap_values.data[0], shap_values.values[0, :, 1]))\n", "    return {\"original\": text, \"interpretation\": scores}\n", "\n", "css = \"footer {display: none !important;} .gradio-container {min-height: 0px !important;}\"\n", "\n", "with gr.Blocks(css=css) as demo:\n", "    with gr.Row():\n", "        with gr.Column():\n", "            input_text = gr.Textbox(label=\"Sentiment Analysis\", value=\"Wonderfully terrible\")\n", "            with gr.Row():\n", "                interpret = gr.Button(\"Interpret\")\n", "        with gr.Column():\n", "                interpretation = gr.components.Interpretation(input_text)\n", "\n", "    interpret.click(interpretation_function, input_text, interpretation)\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

run.py

@@ -0,0 +1,28 @@
+import gradio as gr
+import shap
+from transformers import pipeline
+
+
+sentiment_classifier = pipeline("text-classification", return_all_scores=True)
+
+def interpretation_function(text):
+    explainer = shap.Explainer(sentiment_classifier)
+    shap_values = explainer([text])
+    scores = list(zip(shap_values.data[0], shap_values.values[0, :, 1]))
+    return {"original": text, "interpretation": scores}
+
+css = "footer {display: none !important;} .gradio-container {min-height: 0px !important;}"
+
+with gr.Blocks(css=css) as demo:
+    with gr.Row():
+        with gr.Column():
+            input_text = gr.Textbox(label="Sentiment Analysis", value="Wonderfully terrible")
+            with gr.Row():
+                interpret = gr.Button("Interpret")
+        with gr.Column():
+                interpretation = gr.components.Interpretation(input_text)
+
+    interpret.click(interpretation_function, input_text, interpretation)
+
+if __name__ == "__main__":
+    demo.launch()