File size: 5,753 Bytes
9724ee5
 
 
2b8b510
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
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
244
245
246
247
##Variables

import os
import streamlit as st
import pathlib

from langchain.embeddings import HuggingFaceEmbeddings,HuggingFaceInstructEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.chat_models.openai import ChatOpenAI
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
)

@st.experimental_singleton(suppress_st_warning=True)
def get_latest_file():
    '''Get the latest file from output folder'''

    # set the directory path
    directory_path = "output/"
    
    # create a list of all text files in the directory and sort by modification time
    text_files = sorted(pathlib.Path(directory_path).glob("*.txt"), key=lambda f: f.stat().st_mtime)
    
    # get the latest modified file
    latest_file = text_files[-1]
    
    # open the file and read its contents
    with open(latest_file, "r") as f:
        file_contents = f.read()

    return file_contents

@st.experimental_singleton(suppress_st_warning=True)
def process_tweets(file,embed_model,query):
    '''Process file with latest tweets'''

    # Split tweets int chunks
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
    texts = text_splitter.split_text(file)

    model = bi_enc_dict[embed_model]

    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)

    chain_type_kwargs = {"prompt": prompt}
    chain = VectorDBQA.from_chain_type(
    ChatOpenAI(temperature=0), 
    chain_type="stuff", 
    vectorstore=docsearch,
    chain_type_kwargs=chain_type_kwargs
    )

    result = chain({"query": query}, return_only_outputs=True)

    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",
}

user_name = [
    "Investing.com",
    "(((The Daily Shot)))",
    "Bloomberg Markets",
    "FirstSquawk",
    "MarketWatch",
    "markets",
    "FinancialTimes",
    "CNBC",
    "ReutersBiz",
    "BreakingNews",
    "LiveSquawk",
    "NYSE",
    "WSJmarkets",
    "FT",
    "TheStreet",
    "ftfinancenews",
    "BloombergTV",
    "Nasdaq",
    "NYSE",
    "federalreserve",
    "NewYorkFed",
    "sffed",
    "WSJCentralBanks",
    "RichmondFed",
    "ecb",
    "stlouisfed",
    "WorldBank",
    "MarketCurrents",
    "OpenOutcrier",
    "BullTradeFinder",
    "WallStChatter",
    "Briefingcom",
    "SeekingAlpha",
    "realDonaldTrump",
    "AswathDamodaran",
    "ukarlewitz",
    "alphatrends",
    "Investor666",
    "ACInvestorBlog",
    "ZorTrades",
    "ScottNations",
    "TradersCorner",
    "TraderGoalieOne",
    "option_snipper",
    "jasonleavitt",
    "LMT978",
    "OptionsHawk",
    "andrewbtodd",
    "Terri1618",
    "SunriseTrader",
    "traderstewie",
    "TMLTrader",
    "IncredibleTrade",
    "NYFedResearch",
    "YahooFinance",
    "business",
    "economics",
    "IMFNews",
    "Market_Screener",
    "QuickTake",
    "NewsFromBW",
    "BNCommodities",
]

user_id = [
    "988955288",
    "423769635",
    "69620713",
    "59393368",
    "3295423333",
    "624413",
    "69620713",
    "4898091",
    "20402945",
    "15110357",
    "6017542",
    "21323268",
    "28164923",
    "18949452",
    "15281391",
    "11014272",
    "35002876",
    "18639734",
    "21323268",
    "26538229",
    "15072071",
    "117237387",
    "327484803",
    "16532451",
    "83466368",
    "71567590",
    "27860681",
    "15296897",
    "2334614718",
    "2222635612",
    "3382363841",
    "72928001",
    "23059499",
    "25073877",
    "33216611",
    "37284991",
    "15246621",
    "293458690",
    "55561590",
    "18560146",
    "244978426",
    "85523269",
    "276714687",
    "2806294664",
    "16205561",
    "1064700308",
    "61342056",
    "184126162",
    "405820375",
    "787439438964068352",
    "52166809",
    "2715646770",
    "47247213",
    "374672240",
    "19546277",
    "34713362",
    "144274618",
    "25098482",
    "102325185",
    "252751061",
    "976297820532518914",
    "804556370",
]

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)