Add application file

app.py

@@ -0,0 +1,130 @@
+import streamlit as st
+import pandas as pd
+from transformers import pipeline
+from stqdm import stqdm
+from simplet5 import SimpleT5
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+
+@st.cache
+def load_t5():
+    model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
+
+    tokenizer = AutoTokenizer.from_pretrained("t5-base")
+    return model, tokenizer
+
+
+@st.cache(allow_output_mutation=False)
+def custom_model():
+    return pipeline("summarization", model="my_awesome_sum/")
+
+
+@st.cache
+def convert_df(df):
+    # IMPORTANT: Cache the conversion to prevent computation on every rerun
+    return df.to_csv().encode("utf-8")
+
+
+@st.cache
+def load_one_line_summarizer(model):
+    return model.load_model("t5", "snrspeaks/t5-one-line-summary")
+
+
+st.set_page_config(layout="wide", page_title="Amazon Review Summarizer")
+st.title("Amazon Review Summarizer")
+
+uploaded_file = st.file_uploader("Choose a file", type=["xlsx", "xls", "csv"])
+summarizer_option = st.selectbox(
+    "Select Summarizer",
+    ("Custom trained on the dataset", "t5-base", "t5-one-line-summary"),
+)
+ps = st.empty()
+if st.button("Process"):
+    if uploaded_file is not None:
+
+        df = pd.read_excel(uploaded_file)
+        columns = df.columns.values.tolist()
+        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(10)):
+
+                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()[0:10], "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()
+
+            load_one_line_summarizer(model=model)
+
+            summary = []
+            for x in stqdm(range(10)):
+                try:
+                    summary.append(model.predict(text[x])[0])
+                except:
+                    pass
+            output = pd.DataFrame(
+                {"text": df["text"].values.tolist()[0:10], "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",
+            )

my_awesome_sum/config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

my_awesome_sum/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7360fd249c0844a6561fe1cb3c09b6ef3c298e30010f82af7756a3f3a194e334
+size 242069785

my_awesome_sum/runs/Jan31_20-01-20_DESKTOP-KLKCBUF/1675177280.385954/events.out.tfevents.1675177280.DESKTOP-KLKCBUF.8104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcdf3676c2ab95a48e0e327785fbf42e3c328a92ef353b685a73021a40e8ef5a
+size 5732

my_awesome_sum/runs/Jan31_20-01-20_DESKTOP-KLKCBUF/events.out.tfevents.1675177280.DESKTOP-KLKCBUF.8104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5767b704d6b1c5e43aa1fa1a7865fb4c2c87ba7a3e2c43d3ef893f44a74b158
+size 4645

my_awesome_sum/runs/Jan31_20-16-04_DESKTOP-KLKCBUF/1675178164.489649/events.out.tfevents.1675178164.DESKTOP-KLKCBUF.8104.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f9f0f707a08678a79dbe9c2d767c4fa8155eece008196df1d0f372810d3009
+size 5732

my_awesome_sum/runs/Jan31_20-16-04_DESKTOP-KLKCBUF/events.out.tfevents.1675178164.DESKTOP-KLKCBUF.8104.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b07b8c6dab1cdae47dc001457b325083398d7fc1be04a8c7346536fa823558
+size 5160

my_awesome_sum/runs/Jan31_20-40-37_DESKTOP-KLKCBUF/1675179637.5629804/events.out.tfevents.1675179637.DESKTOP-KLKCBUF.8408.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7321bd13cc6053881a99fee797b79f1b1a2ce1534de079cd7833897c855bc110
+size 5732

my_awesome_sum/runs/Jan31_20-40-37_DESKTOP-KLKCBUF/events.out.tfevents.1675179637.DESKTOP-KLKCBUF.8408.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ae99c27bbdb92be4abcff90dfc322810a923ca2c6610b24800a1d3dc967086
+size 6190

my_awesome_sum/runs/Jan31_21-41-54_DESKTOP-KLKCBUF/1675183314.294505/events.out.tfevents.1675183314.DESKTOP-KLKCBUF.13020.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1f7366c32892d4febbf4f3116ec76d40132effe0c90102f9c3a3d0871ce9e0
+size 5732

my_awesome_sum/runs/Jan31_21-41-54_DESKTOP-KLKCBUF/events.out.tfevents.1675183314.DESKTOP-KLKCBUF.13020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00a06db943cbe4cc33313ba15d494509a5321a54bfa6bba0bb7d293954257cf
+size 7053

my_awesome_sum/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

my_awesome_sum/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "t5-small",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

my_awesome_sum/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a2729479e1b383a832c67d41adbc899ddea624695c5d9463aebab5cb899292
+size 3515

requirements.txt

@@ -0,0 +1,8 @@
+openpyxl
+pandas
+simplet5
+streamlit==1.11.0
+transformers==4.16.2
+stqdm
+torch
+bert-extractive-summarizer