Spaces:
Running
on
T4
Running
on
T4
File size: 10,249 Bytes
8d31bb0 aebf357 9251391 00031a8 204c916 9251391 11569de aebf357 00031a8 9251391 1f03788 aebf357 adde38c 9251391 aebf357 69f6ec4 aebf357 adde38c 02ac1ae aebf357 02ac1ae aebf357 e732bbf aebf357 1f03788 9251391 204c916 11569de 204c916 aebf357 9251391 aebf357 9251391 aebf357 9251391 aebf357 9251391 aebf357 9251391 00031a8 9251391 00031a8 9251391 00031a8 9251391 82047ec 11569de 9251391 00031a8 9251391 82047ec 9251391 1f03788 9251391 00031a8 9251391 aebf357 812370d aebf357 927b6fc aebf357 9251391 a54d7cf 9251391 927b6fc aebf357 835cde3 9251391 835cde3 aebf357 204c916 aebf357 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 |
import os
import re
import time
import json
import random
import finnhub
import torch
import gradio as gr
import pandas as pd
import yfinance as yf
from pynvml import *
from peft import PeftModel
from collections import defaultdict
from datetime import date, datetime, timedelta
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
access_token = os.environ["HF_TOKEN"]
finnhub_client = finnhub.Client(api_key=os.environ["FINNHUB_API_KEY"])
base_model = AutoModelForCausalLM.from_pretrained(
'meta-llama/Llama-2-7b-chat-hf',
token=access_token,
trust_remote_code=True,
device_map="auto",
torch_dtype=torch.float16,
offload_folder="offload/"
)
model = PeftModel.from_pretrained(
base_model,
'FinGPT/fingpt-forecaster_dow30_llama2-7b_lora',
offload_folder="offload/"
)
model = model.eval()
tokenizer = AutoTokenizer.from_pretrained(
'meta-llama/Llama-2-7b-chat-hf',
token=access_token
)
streamer = TextStreamer(tokenizer)
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
SYSTEM_PROMPT = "You are a seasoned stock market analyst. Your task is to list the positive developments and potential concerns for companies based on relevant news and basic financials from the past weeks, then provide an analysis and prediction for the companies' stock price movement for the upcoming week. " \
"Your answer format should be as follows:\n\n[Positive Developments]:\n1. ...\n\n[Potential Concerns]:\n1. ...\n\n[Prediction & Analysis]\nPrediction: ...\nAnalysis: ..."
def print_gpu_utilization():
nvmlInit()
handle = nvmlDeviceGetHandleByIndex(0)
info = nvmlDeviceGetMemoryInfo(handle)
print(f"GPU memory occupied: {info.used//1024**2} MB.")
def get_curday():
return date.today().strftime("%Y-%m-%d")
def n_weeks_before(date_string, n):
date = datetime.strptime(date_string, "%Y-%m-%d") - timedelta(days=7*n)
return date.strftime("%Y-%m-%d")
def get_stock_data(stock_symbol, steps):
stock_data = yf.download(stock_symbol, steps[0], steps[-1])
# print(stock_data)
dates, prices = [], []
available_dates = stock_data.index.format()
for date in steps[:-1]:
for i in range(len(stock_data)):
if available_dates[i] >= date:
prices.append(stock_data['Close'][i])
dates.append(datetime.strptime(available_dates[i], "%Y-%m-%d"))
break
dates.append(datetime.strptime(available_dates[-1], "%Y-%m-%d"))
prices.append(stock_data['Close'][-1])
return pd.DataFrame({
"Start Date": dates[:-1], "End Date": dates[1:],
"Start Price": prices[:-1], "End Price": prices[1:]
})
def get_news(symbol, data):
news_list = []
for end_date, row in data.iterrows():
start_date = row['Start Date'].strftime('%Y-%m-%d')
end_date = row['End Date'].strftime('%Y-%m-%d')
# print(symbol, ': ', start_date, ' - ', end_date)
time.sleep(1) # control qpm
weekly_news = finnhub_client.company_news(symbol, _from=start_date, to=end_date)
weekly_news = [
{
"date": datetime.fromtimestamp(n['datetime']).strftime('%Y%m%d%H%M%S'),
"headline": n['headline'],
"summary": n['summary'],
} for n in weekly_news
]
weekly_news.sort(key=lambda x: x['date'])
news_list.append(json.dumps(weekly_news))
data['News'] = news_list
return data
def get_company_prompt(symbol):
profile = finnhub_client.company_profile2(symbol=symbol)
company_template = "[Company Introduction]:\n\n{name} is a leading entity in the {finnhubIndustry} sector. Incorporated and publicly traded since {ipo}, the company has established its reputation as one of the key players in the market. As of today, {name} has a market capitalization of {marketCapitalization:.2f} in {currency}, with {shareOutstanding:.2f} shares outstanding." \
"\n\n{name} operates primarily in the {country}, trading under the ticker {ticker} on the {exchange}. As a dominant force in the {finnhubIndustry} space, the company continues to innovate and drive progress within the industry."
formatted_str = company_template.format(**profile)
return formatted_str
def get_prompt_by_row(symbol, row):
start_date = row['Start Date'] if isinstance(row['Start Date'], str) else row['Start Date'].strftime('%Y-%m-%d')
end_date = row['End Date'] if isinstance(row['End Date'], str) else row['End Date'].strftime('%Y-%m-%d')
term = 'increased' if row['End Price'] > row['Start Price'] else 'decreased'
head = "From {} to {}, {}'s stock price {} from {:.2f} to {:.2f}. Company news during this period are listed below:\n\n".format(
start_date, end_date, symbol, term, row['Start Price'], row['End Price'])
news = json.loads(row["News"])
news = ["[Headline]: {}\n[Summary]: {}\n".format(
n['headline'], n['summary']) for n in news if n['date'][:8] <= end_date.replace('-', '') and \
not n['summary'].startswith("Looking for stock market analysis and research with proves results?")]
basics = json.loads(row['Basics'])
if basics:
basics = "Some recent basic financials of {}, reported at {}, are presented below:\n\n[Basic Financials]:\n\n".format(
symbol, basics['period']) + "\n".join(f"{k}: {v}" for k, v in basics.items() if k != 'period')
else:
basics = "[Basic Financials]:\n\nNo basic financial reported."
return head, news, basics
def sample_news(news, k=5):
return [news[i] for i in sorted(random.sample(range(len(news)), k))]
def get_current_basics(symbol, curday):
basic_financials = finnhub_client.company_basic_financials(symbol, 'all')
final_basics, basic_list, basic_dict = [], [], defaultdict(dict)
for metric, value_list in basic_financials['series']['quarterly'].items():
for value in value_list:
basic_dict[value['period']].update({metric: value['v']})
for k, v in basic_dict.items():
v.update({'period': k})
basic_list.append(v)
basic_list.sort(key=lambda x: x['period'])
for basic in basic_list[::-1]:
if basic['period'] <= curday:
break
return basic
def get_all_prompts_online(symbol, data, curday, with_basics=True):
company_prompt = get_company_prompt(symbol)
prev_rows = []
for row_idx, row in data.iterrows():
head, news, _ = get_prompt_by_row(symbol, row)
prev_rows.append((head, news, None))
prompt = ""
for i in range(-len(prev_rows), 0):
prompt += "\n" + prev_rows[i][0]
sampled_news = sample_news(
prev_rows[i][1],
min(5, len(prev_rows[i][1]))
)
if sampled_news:
prompt += "\n".join(sampled_news)
else:
prompt += "No relative news reported."
period = "{} to {}".format(curday, n_weeks_before(curday, -1))
if with_basics:
basics = get_current_basics(symbol, curday)
basics = "Some recent basic financials of {}, reported at {}, are presented below:\n\n[Basic Financials]:\n\n".format(
symbol, basics['period']) + "\n".join(f"{k}: {v}" for k, v in basics.items() if k != 'period')
else:
basics = "[Basic Financials]:\n\nNo basic financial reported."
info = company_prompt + '\n' + prompt + '\n' + basics
prompt = info + f"\n\nBased on all the information before {curday}, let's first analyze the positive developments and potential concerns for {symbol}. Come up with 2-4 most important factors respectively and keep them concise. Most factors should be inferred from company related news. " \
f"Then make your prediction of the {symbol} stock price movement for next week ({period}). Provide a summary analysis to support your prediction."
return info, prompt
def construct_prompt(ticker, curday, n_weeks, use_basics):
steps = [n_weeks_before(curday, n) for n in range(n_weeks + 1)][::-1]
data = get_stock_data(ticker, steps)
data = get_news(ticker, data)
data['Basics'] = [json.dumps({})] * len(data)
print(data)
info, prompt = get_all_prompts_online(ticker, data, curday, use_basics)
prompt = B_INST + B_SYS + SYSTEM_PROMPT + E_SYS + prompt + E_INST
print(prompt)
return info, prompt
def predict(ticker, date, n_weeks, use_basics):
print_gpu_utilization()
info, prompt = construct_prompt(ticker, date, n_weeks, use_basics)
inputs = tokenizer(
prompt, return_tensors='pt', padding=False
)
inputs = {key: value.to(model.device) for key, value in inputs.items()}
print("Inputs loaded onto devices.")
res = model.generate(
**inputs, max_length=4096, do_sample=True,
eos_token_id=tokenizer.eos_token_id,
use_cache=True, streamer=streamer
)
output = tokenizer.decode(res[0], skip_special_tokens=True)
answer = re.sub(r'.*\[/INST\]\s*', '', output, flags=re.DOTALL)
torch.cuda.empty_cache()
return info, answer
demo = gr.Interface(
predict,
inputs=[
gr.Textbox(
label="Ticker",
value="AAPL",
info="Companys from Dow-30 are recommended"
),
gr.Textbox(
label="Date",
value=get_curday,
info="Date from which the prediction is made, use format yyyy-mm-dd"
),
gr.Slider(
minimum=1,
maximum=4,
value=3,
step=1,
label="n_weeks",
info="Information of the past n weeks will be utilized, choose between 1 and 4"
),
gr.Checkbox(
label="Use Latest Financial Basics",
value=False,
info="If checked, the latest quarterly reported financial basics of the company is taken into account."
)
],
outputs=[
gr.Textbox(
label="Information"
),
gr.Textbox(
label="Response"
)
]
)
demo.launch()
|