How to Build a Python Stock Temperature Analyzer with Tushare

1. Get Data

Import the tushare package, set your token, and call the daily_basic interface to retrieve daily fundamental indicators (PE, PB, etc.) for a given stock over a ten‑year period.

# import package
import tushare as ts

# token (obtain from https://tushare.pro/register)
ts_token = 'YOUR_TOKEN'

pro = ts.pro_api(ts_token)

# date range
import datetime
days = 365 * 10
end_date = datetime.date.today().strftime('%Y%m%d')
start_date = (datetime.date.today() - datetime.timedelta(days=days)).strftime('%Y%m%d')

# fetch data
stock_data = pro.daily_basic(ts_code='000001.SZ',
                             start_date=start_date,
                             end_date=end_date,
                             fields='ts_code,trade_date,close,turnover_rate,volume_ratio,pe,pb,total_mv')

2. Process Data

Use numpy to compute rolling means and standard deviations of pe and pb, then apply the normal cumulative distribution function from scipy.stats to obtain a “temperature” value (scaled to 0‑100) for each day.

# import packages
import numpy as np
import scipy.stats as st

# initialise temperature columns
stock_data['pe_temperature'] = 0.5
stock_data['pb_temperature'] = 0.5

for i in range(1, len(stock_data)):
    # PE
    mean = np.mean(stock_data['pe'][:i+1])
    std = np.std(stock_data['pe'][:i+1], ddof=1)
    stock_data['pe_temperature'].iloc[i] = st.norm.cdf(stock_data['pe'].iloc[i], loc=mean, scale=std)
    # PB
    mean = np.mean(stock_data['pb'][:i+1])
    std = np.std(stock_data['pb'][:i+1], ddof=1)
    stock_data['pb_temperature'].iloc[i] = st.norm.cdf(stock_data['pb'].iloc[i], loc=mean, scale=std)

# combine into a single temperature
stock_data['temperature'] = (stock_data['pe_temperature'] + stock_data['pb_temperature']) * 50

3. Visualise Results

Sort the data by trade date and plot the temperature together with the closing price using matplotlib. The left y‑axis shows the temperature, the right y‑axis shows the closing price.

# import matplotlib
import matplotlib.pyplot as plt
from matplotlib.ticker import MultipleLocator

stock_data.sort_values(by='trade_date', ascending=True, inplace=True)

fig, ax1 = plt.subplots()
ax1.set_title('stock temperature')
ax1.set_xlabel('time')
ax1.set_ylabel('temperature')

ax2 = ax1.twinx()
ax2.set_ylabel('close')

data_len = stock_data.shape[0]
locator = MultipleLocator(data_len/10)
ax1.xaxis.set_major_locator(locator)
ax2.xaxis.set_major_locator(locator)

ax1.plot(stock_data['trade_date'], stock_data['temperature'],
         linestyle='--', marker='.', alpha=0.5, color='r', label='temperature')
ax2.plot(stock_data['trade_date'], stock_data['close'],
         linestyle='-', marker='.', color='g', label='close')

ax1.legend(loc='upper left')
ax2.legend(loc='upper right')
plt.show()

The resulting chart displays the stock’s temperature curve alongside its closing price over time.