get_timeseries_rolling_directional_changes This function performs a rolling analysis on your data to identify if a directional change is forecasted for the final period within each window. This is ideal for backtesting or observing how trends evolve over time.

​
Function Parameters

ParameterTypeRequiredDescription
data_inputobjectTrueThe financial time series data to be analysed. This can be a file path (e.g., ‘folder/ohlc_data.csv’) or a pandas DataFrame. Supported file formats include CSV, TSV, Parquet, Excel, JSON, and HTML.
intervalintTrueThe frequency of the time series data. Use in conjunction with interval_unit.
interval_unitstringTrueThe unit of time for the interval. Accepts one of the following values: ‘seconds’, ‘minutes’ and ‘days’.
reasoning_modestringTrueThe reasoning strategy the architecture uses to make decisions: ‘proactive’ acts early with minimal information while ‘reactive’ waits for sufficient evidence before acting.
output_filestringTrueThe name of the file where the output will be saved. The output is a CSV file. For example, ‘saved_output’ will create saved_output.csv.

​
Data Columns

Your input data (file or DataFrame) must contain the following columns:
  • datetime (string): A timestamp for each data point.
  • open (float): The opening price for the interval.
  • high (float): The highest price reached during the interval.
  • low (float): The lowest price reached during the interval.
  • close (float): The closing price for the interval.

​
Python Code Example

# Performs a rolling window analysis on the observed data

rolling_trends = client.get_timeseries_rolling_directional_changes(
    data_input='folder/ohlc_data.csv', # or can be a pandas dataframe 
    interval=1,
    interval_unit='days',
    reasoning_mode='proactive',
    window_size=5001,
    output_file='saved_output'
)

# Returns a dataframe with columns: [datetime, trend_identified]
# Trend values: 1 (positive change), -1 (negative change), 0 (no clear change)