Update app.py

app.py

@@ -1,63 +1,81 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import streamlit as st
+import wna_googlenews as wna
+import pandas as pd
+from transformers import pipeline
+
+st.set_page_config(layout="wide")
+
+st.title("WNA Google News App")
+st.subheader("Search for News and classify the headlines with sentiment analysis")
+
+query = st.text_input("Enter Query")
+
+models = [
+          "j-hartmann/emotion-english-distilroberta-base",
+          "SamLowe/roberta-base-go_emotions"
+          # "distilbert/distilbert-base-uncased-finetuned-sst-2-english"
+        ]
+
+settings = {
+  "langregion": "en/US",
+  "period": "1d",
+  "model": models[0],
+  "number_of_pages": 5
+}
+
+
+with st.sidebar:
+  st.title("Settings")
+  # add language and country parameters
+  st.header("Language and Country")
+  
+  settings["langregion"] = st.selectbox("Select Language", ["en/US", "fr/FR"])
+  # input field for number of pages
+  st.header("Number of Pages")
+  settings["number_of_pages"] = st.number_input("Enter Number of Pages", min_value=1, max_value=10)
+
+  settings["region"] = settings["langregion"].split("/")[0]
+  settings["lang"] = settings["langregion"].split("/")[1]
+
+  # add period parameter
+  st.header("Period")
+  settings["period"] = st.selectbox("Select Period", ["1d", "7d", "30d"])
+  # Add models parameters
+  st.header("Models")
+  settings["model"] = st.selectbox("Select Model", models)
+
+
+if st.button("Search"):
+  classifier = pipeline(task="text-classification", model=settings["model"], top_k=None)
+  # display a loading progress
+  with st.spinner("Loading last news ..."):
+    allnews = wna.get_news(settings, query)
+    st.dataframe(allnews)
+  with st.spinner("Processing received news ..."):
+    df = pd.DataFrame(columns=["sentence", "date","best","second"])
+    # loop on each sentence and call classifier
+    for curnews in allnews:
+      #st.write(curnews)
+      cur_sentence = curnews["title"]
+      cur_date = curnews["date"]
+      model_outputs = classifier(cur_sentence)
+      cur_result = model_outputs[0]
+      #st.write(cur_result)
+      # get label 1
+      label = cur_result[0]['label']
+      score = cur_result[0]['score']
+      percentage = round(score * 100, 2)
+      str1 = label + " (" + str(percentage) + ")%"
+      # get label 2
+      label = cur_result[1]['label']
+      score = cur_result[1]['score']
+      percentage = round(score * 100, 2)
+      str2 = label + " (" + str(percentage) + ")%"
+      # insert cur_sentence and cur_result into dataframe
+      df.loc[len(df.index)] = [cur_sentence, cur_date, str1, str2]
+
+  # write info on the output
+  st.write("Number of sentences:", len(df))
+  st.write("Language:", settings["lang"], "Country:", settings["region"])
+
+  st.dataframe(df)