Update app.py

app.py

@@ -58,84 +58,96 @@ if st.button("Process"):
         columns = [x.lower() for x in columns]
         df.columns = columns
         print(summarizer_option)
-        if summarizer_option == "Custom trained on the dataset":
-            model = custom_model()
-            print(summarizer_option)
-            text = df["text"].values.tolist()
-            progress_text = "Summarization in progress. Please wait."
-            summary = []
-
-            for x in stqdm(range(len(text))):
-                try:
-                    summary.append(
-                        model(
-                            f"summarize: {text[x]}", max_length=50, early_stopping=True
-                        )[0]["summary_text"]
-                    )
-                except:
-                    pass
-            output = pd.DataFrame(
-                {"text": df["text"].values.tolist(), "summary": summary}
-            )
-            csv = convert_df(output)
-            st.download_button(
-                label="Download data as CSV",
-                data=csv,
-                file_name=f"{summarizer_option}_df.csv",
-                mime="text/csv",
-            )
-        if summarizer_option == "t5-base":
-            model, tokenizer = load_t5()
-            text = df["text"].values.tolist()
-            summary = []
-            for x in stqdm(range(len(text))):
-
-                tokens_input = tokenizer.encode(
-                    "summarize: " + text[x],
-                    return_tensors="pt",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
+        try:
+
+            if summarizer_option == "Custom trained on the dataset":
+                model = custom_model()
+                print(summarizer_option)
+                text = df["text"].values.tolist()
+                progress_text = "Summarization in progress. Please wait."
+                summary = []
+
+                for x in stqdm(range(len(text))):
+                    try:
+                        summary.append(
+                            model(
+                                f"summarize: {text[x]}",
+                                max_length=50,
+                                early_stopping=True,
+                            )[0]["summary_text"]
+                        )
+                    except:
+                        pass
+                output = pd.DataFrame(
+                    {"text": df["text"].values.tolist(), "summary": summary}
                 )
-                summary_ids = model.generate(
-                    tokens_input,
-                    min_length=80,
-                    max_length=150,
-                    length_penalty=20,
-                    num_beams=2,
+                csv = convert_df(output)
+                st.download_button(
+                    label="Download data as CSV",
+                    data=csv,
+                    file_name=f"{summarizer_option}_df.csv",
+                    mime="text/csv",
                 )
-                summary_gen = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-                summary.append(summary_gen)
+            if summarizer_option == "t5-base":
+                model, tokenizer = load_t5()
+                text = df["text"].values.tolist()
+                summary = []
+                for x in stqdm(range(len(text))):
+
+                    tokens_input = tokenizer.encode(
+                        "summarize: " + text[x],
+                        return_tensors="pt",
+                        max_length=tokenizer.model_max_length,
+                        truncation=True,
+                    )
+                    summary_ids = model.generate(
+                        tokens_input,
+                        min_length=80,
+                        max_length=150,
+                        length_penalty=20,
+                        num_beams=2,
+                    )
+                    summary_gen = tokenizer.decode(
+                        summary_ids[0], skip_special_tokens=True
+                    )
+                    summary.append(summary_gen)
 
-            output = pd.DataFrame(
-                {"text": df["text"].values.tolist(), "summary": summary}
-            )
-            csv = convert_df(output)
-            st.download_button(
-                label="Download data as CSV",
-                data=csv,
-                file_name=f"{summarizer_option}_df.csv",
-                mime="text/csv",
-            )
+                output = pd.DataFrame(
+                    {"text": df["text"].values.tolist(), "summary": summary}
+                )
+                csv = convert_df(output)
+                st.download_button(
+                    label="Download data as CSV",
+                    data=csv,
+                    file_name=f"{summarizer_option}_df.csv",
+                    mime="text/csv",
+                )
 
-        if summarizer_option == "t5-one-line-summary":
-            model = SimpleT5()
-            text = df["text"].values.tolist()
+            if summarizer_option == "t5-one-line-summary":
+                model = SimpleT5()
+                text = df["text"].values.tolist()
 
-            load_one_line_summarizer(model=model)
+                load_one_line_summarizer(model=model)
 
-            summary = []
-            for x in stqdm(range(len(text))):
-                try:
-                    summary.append(model.predict(text[x])[0])
-                except:
-                    pass
-            output = pd.DataFrame(
-                {"text": df["text"].values.tolist(), "summary": summary}
-            )
-            csv = convert_df(output)
-            st.download_button(
-                label="Download data as CSV",
-                data=csv,
-                file_name=f"{summarizer_option}_df.csv",
-                mime="text/csv",
+                summary = []
+                for x in stqdm(range(len(text))):
+                    try:
+                        summary.append(model.predict(text[x])[0])
+                    except:
+                        pass
+                output = pd.DataFrame(
+                    {"text": df["text"].values.tolist(), "summary": summary}
+                )
+                csv = convert_df(output)
+                st.download_button(
+                    label="Download data as CSV",
+                    data=csv,
+                    file_name=f"{summarizer_option}_df.csv",
+                    mime="text/csv",
+                )
+        except KeyError:
+            st.error(
+                "Please Make sure that your data must have a column named text",
+                icon="🚨",
             )
+            st.info("Text column must have amazon reviews", icon="ℹ️")