fingpt/FinGPT_Others/FinGPT_Low_Code_Development/chatgpt-low-code-development-v2/readme.md

ChatGPT Low Code Development V2: Finding New Factors

In addition to factor development, the quest for identifying effective factors is also a challenging journey. Our demo can expedite this process through the use of tailored prompts.

Round 1

init prompt:

Now, you are a senior professional stock factor researcher in top financial companies.You will help me to build some factors in Python today.

ChatGPT's response (More in this file):

Of course! I'd be happy to help you build some factors in Python. Please let me know what specific factors you would like to build or if you have any specific requirements in mind.

Round 2

prompt 1:

Let's look at the data, it's stored in the CSV format and has the following columns: open, high, low, close, volume, and amount.

ChatGPT's response (More in this file):

Great! To begin, we'll start by loading the data from the CSV file into a pandas DataFrame. Assuming the file is named "data.csv" and is located in the current working directory, you can use the following code:

import pandas as pd

# Load data from CSV into a DataFrame
data = pd.read_csv('data.csv')

# Display a preview of the data
print(data.head())

...

Round 3

prompt 2:

OK. First, please show me a function to calculate the Fundamental Momentum Factor. Let's use FMF to indicate Fundamental Momentum Factor.

ChatGPT's response (More in this file):

The Fundamental Momentum Factor (FMF) is a measure that quantifies the change in fundamental metrics over a specific period. To calculate the FMF, we need to select a fundamental metric (e.g., "amount") and a time period (e.g., 1 year). Here's how you can calculate the FMF in Python:

import pandas as pd

def calculate_fmf(data, metric, period):
    # Convert the date column to datetime format
    data['date'] = pd.to_datetime(data['date'])
    
    # Sort the data by date in ascending order
    data = data.sort_values('date')
    
    # Calculate the FMF
    data['fmf'] = data[metric].pct_change(periods=period)
    
    return data

# Load data from CSV into a DataFrame
data = pd.read_csv('data.csv')

# Calculate FMF using the 'amount' metric over a 1-year period
fmf_data = calculate_fmf(data, 'amount', 252)

# Display a preview of the FMF data
print(fmf_data.head())

...

Round 4

prompt 3:

Next, please show me a function to calculate the Price Momentum Factor. Let's use PMF to indicate Price Momentum Factor.

ChatGPT's response (More in this file):

The Price Momentum Factor (PMF) is a measure that quantifies the price momentum of a stock. It is typically calculated as the percentage change in the closing price over a specific period. Here's how you can calculate the PMF in Python:

import pandas as pd

def calculate_pmf(data, period):
    # Convert the date column to datetime format
    data['date'] = pd.to_datetime(data['date'])
    
    # Sort the data by date in ascending order
    data = data.sort_values('date')
    
    # Calculate the PMF
    data['pmf'] = data['close'].pct_change(periods=period)
    
    return data

# Load data from CSV into a DataFrame
data = pd.read_csv('data.csv')

# Calculate PMF over a 1-year period
pmf_data = calculate_pmf(data, 252)

# Display a preview of the PMF data
print(pmf_data.head())

...

Round 5

prompt 4:

Next, please show me a function to calculate the Price Momentum Factor. Let's use PMF to indicate Price Momentum Factor.

ChatGPT's response (More in this file):

Certainly! Let's combine the Fundamental Momentum Factor (FMF) and Price Momentum Factor (PMF) functions to create a more complex stock factor. Here's an example of how we can do it step by step:

1. Calculate FMF:

   fmf_data = calculate_fmf(data, 'amount', 252)
   

2. Calculate PMF:

   pmf_data = calculate_pmf(data, 252)
   

3. Merge FMF and PMF data on the 'date' column:

   merged_data = pd.merge(fmf_data, pmf_data[['date', 'pmf']], on='date', how='inner')
   

4. Create a new factor by multiplying FMF and PMF:

   merged_data['complex_factor'] = merged_data['fmf'] * merged_data['pmf']
   

5. Optionally, you may want to normalize the complex factor to a certain range or scale for easier interpretation. For instance, you can use the Min-Max scaling method:

   merged_data['complex_factor_scaled'] = (merged_data['complex_factor'] - merged_data['complex_factor'].min()) / (merged_data['complex_factor'].max() - merged_data['complex_factor'].min())
   

...