Spaces:
Build error
Build error
File size: 4,968 Bytes
9724ee5 2b8b510 b3ad6ec 2b8b510 6fd7c54 b628185 2b8b510 67ed4d1 9cadbe9 2b8b510 9cadbe9 5ec18f4 9cadbe9 b3ad6ec 3e6c28b 2b8b510 5ec18f4 1dc65be e265b8a 3e45e67 2b8b510 88cec00 2b8b510 9724ee5 23e4bc0 9724ee5 |
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 |
##Variables
import os
import streamlit as st
import pathlib
from langchain.embeddings import HuggingFaceEmbeddings,HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models.openai import ChatOpenAI
from langchain.callbacks.base import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain import VectorDBQA
import pandas as pd
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
AIMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage
)
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline, AutoTokenizer
from optimum.pipelines import pipeline
import tweepy
import pandas as pd
import numpy as np
import plotly_express as px
import plotly.graph_objects as go
from datetime import datetime as dt
from st_aggrid import GridOptionsBuilder, AgGrid, GridUpdateMode, DataReturnMode
from datasets import Dataset
from huggingface_hub import Repository
@st.experimental_singleton(suppress_st_warning=True)
def load_models():
'''load sentimant and topic clssification models'''
sent_pipe = pipeline(task,model=sent_model_id, tokenizer=sent_model_id)
topic_pipe = pipeline(task, model=topic_model_id, tokenizer=topic_model_id)
return sent_pipe, topic_pipe
@st.cache(allow_output_mutation=True, suppress_st_warning=True)
def process_tweets(df,df_users):
'''process tweets into a dataframe'''
df['author'] = df['author'].astype(np.int64)
df_merged = df.merge(df_users, on='author')
tweet_list = df_merged['tweet'].tolist()
sentiment, topic = pd.DataFrame(sentiment_classifier(tweet_list)), pd.DataFrame(topic_classifier(tweet_list))
sentiment.rename(columns={'score':'sentiment_confidence','label':'sentiment'}, inplace=True)
topic.rename(columns={'score':'topic_confidence','label':'topic'}, inplace=True)
df_group = pd.concat([df_merged,sentiment,topic],axis=1)
df_group[['sentiment_confidence','topic_confidence']] = df_group[['sentiment_confidence','topic_confidence']].round(2).mul(100)
df_tweets = df_group[['creation_time','username','tweet','sentiment','topic','sentiment_confidence','topic_confidence']]
df_tweets = df_tweets.sort_values(by=['creation_time'],ascending=False)
return df_tweets
@st.experimental_singleton(suppress_st_warning=True)
def create_vectorstore(texts,model):
'''Create FAISS vectorstore'''
if model == "hkunlp/instructor-large":
emb = HuggingFaceInstructEmbeddings(model_name=model,
query_instruction='Represent the Financial question for retrieving supporting documents: ',
embed_instruction='Represent the Financial document for retrieval: ')
elif model == "sentence-transformers/all-mpnet-base-v2":
emb = HuggingFaceEmbeddings(model_name=model)
docsearch = FAISS.from_texts(texts, emb)
return docsearch
@st.experimental_singleton(suppress_st_warning=True)
def embed_tweets(query,_prompt,_docsearch):
'''Process file with latest tweets'''
streaming_llm = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)
chain_type_kwargs = {"prompt": _prompt}
chain = VectorDBQA.from_chain_type(
ChatOpenAI(temperature=0),
chain_type="stuff",
vectorstore=_docsearch,
chain_type_kwargs=chain_type_kwargs,
return_source_documents=True,
k=5
)
result = chain({"query": query})
return result
CONFIG = {
"bearer_token": os.environ.get("bearer_token")
}
sent_model_id = 'nickmuchi/optimum-finbert-tone-finetuned-fintwitter-classification'
topic_model_id = 'nickmuchi/optimum-finbert-tone-finetuned-finance-topic-classification'
task = 'text-classification'
sentiments = {"0": "Bearish", "1": "Bullish", "2": "Neutral"}
topics = {
"0": "Analyst Update",
"1": "Fed | Central Banks",
"2": "Company | Product News",
"3": "Treasuries | Corporate Debt",
"4": "Dividend",
"5": "Earnings",
"6": "Energy | Oil",
"7": "Financials",
"8": "Currencies",
"9": "General News | Opinion",
"10": "Gold | Metals | Materials",
"11": "IPO",
"12": "Legal | Regulation",
"13": "M&A | Investments",
"14": "Macro",
"15": "Markets",
"16": "Politics",
"17": "Personnel Change",
"18": "Stock Commentary",
"19": "Stock Movement",
}
sentiment_classifier, topic_classifier = load_models()
def convert_user_names(user_name: list):
'''convert user_names to tweepy format'''
users = []
for user in user_name:
users.append(f"from:{user}")
return " OR ".join(users) |