Spaces:
Running
Running
File size: 8,928 Bytes
6f595b5 4e736ad e6730c8 66c205b 4e736ad 3902384 6f595b5 3902384 6f595b5 3086575 6f595b5 3902384 6f595b5 3902384 4e736ad 6f595b5 4e736ad 0302fc1 e7ee4c6 6f595b5 1f4c994 6f595b5 e7ee4c6 6f595b5 e7ee4c6 6f595b5 4022606 fecaa45 4022606 4e736ad 4022606 6f595b5 4e736ad 4022606 4e736ad 4022606 6f595b5 4022606 6f595b5 4022606 4e736ad 7673771 4e736ad 4022606 4e736ad 4022606 6f595b5 4022606 6f595b5 4022606 4e736ad 7673771 4e736ad 4022606 4e736ad 4022606 4e736ad 4022606 6f595b5 4022606 4e736ad 7673771 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 |
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
from transformers import BertTokenizer
from tensorflow.keras.models import load_model
from tensorflow.nn import softmax
import numpy as np
from datetime import datetime
import logging
date = datetime.now().strftime(r"%Y-%m-%d")
model_classes = {
0: 'Ads',
1: 'Apps',
2: 'Battery',
3: 'Charging',
4: 'Delivery',
5: 'Display',
6: 'FOS',
7: 'HW',
8: 'Order',
9: 'Refurb',
10: 'SD',
11: 'Setup',
12: 'Unknown'}
@st.cache
def load_t5():
model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
tokenizer = AutoTokenizer.from_pretrained("t5-base")
return model, tokenizer
@st.cache
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(index=False).encode("utf-8")
@st.cache
def load_one_line_summarizer(model):
return model.load_model("t5", "snrspeaks/t5-one-line-summary")
@st.cache
def classify_category():
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
new_model = load_model("model")
return tokenizer, new_model
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"),
)
classification = st.checkbox("Classify Category", value=True)
hide_streamlit_style = """
<style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style>
"""
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
ps = st.empty()
if st.button("Process",type="primary"):
if uploaded_file is not None:
if uploaded_file.name.split(".")[-1] in ["xls", "xlsx"]:
df = pd.read_excel(uploaded_file, engine="openpyxl")
if uploaded_file.name.split(".")[-1] in [".csv"]:
df = pd.read_csv(uploaded_file)
columns = df.columns.values.tolist()
columns = [x.lower() for x in columns]
df.columns = columns
print(summarizer_option)
try:
text = df["text"].values.tolist()
if summarizer_option == "Custom trained on the dataset":
model = custom_model()
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}
)
if classification:
classification_token, classification_model = classify_category()
tf_batch = classification_token(
text,
max_length=128,
padding=True,
truncation=True,
return_tensors="tf",
)
with st.spinner(text="identifying theme"):
tf_outputs = classification_model(tf_batch)
classes = []
with st.spinner(text="creating output file"):
for x in stqdm(range(len(text))):
tf_o = softmax(tf_outputs["logits"][x], axis=-1)
label = np.argmax(tf_o, axis=0)
keys = model_classes
classes.append(keys.get(label))
output["category"] = classes
csv = convert_df(output)
st.download_button(
label="Download data as CSV",
data=csv,
file_name=f"{summarizer_option}_{date}_df.csv",
mime="text/csv",
)
if summarizer_option == "t5-base":
model, tokenizer = load_t5()
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}
)
if classification:
classification_token, classification_model = classify_category()
tf_batch = classification_token(
text,
max_length=128,
padding=True,
truncation=True,
return_tensors="tf",
)
with st.spinner(text="identifying theme"):
tf_outputs = classification_model(tf_batch)
classes = []
with st.spinner(text="creating output file"):
for x in stqdm(range(len(text))):
tf_o = softmax(tf_outputs["logits"][x], axis=-1)
label = np.argmax(tf_o, axis=0)
keys = model_classes
classes.append(keys.get(label))
output["category"] = classes
csv = convert_df(output)
st.download_button(
label="Download data as CSV",
data=csv,
file_name=f"{summarizer_option}_{date}_df.csv",
mime="text/csv",
)
if summarizer_option == "t5-one-line-summary":
model = SimpleT5()
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}
)
if classification:
classification_token, classification_model = classify_category()
tf_batch = classification_token(
text,
max_length=128,
padding=True,
truncation=True,
return_tensors="tf",
)
with st.spinner(text="identifying theme"):
tf_outputs = classification_model(tf_batch)
classes = []
with st.spinner(text="creating output file"):
for x in stqdm(range(len(text))):
tf_o = softmax(tf_outputs["logits"][x], axis=-1)
label = np.argmax(tf_o, axis=0)
keys = model_classes
classes.append(keys.get(label))
output["category"] = classes
csv = convert_df(output)
st.download_button(
label="Download data as CSV",
data=csv,
file_name=f"{summarizer_option}_{date}_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")
except BaseException as e:
logging.exception("An exception was occurred")
|