Calculate cross-sectional standard deviation

Delete all bar data with given symbol + exchange + interval.

Delete all tick data with given symbol + exchange.

Output detailed information about the model

Output MLP model detail information Returns ------- pd.DataFrame Feature importance dataframe

Display model details with feature importance plots Generates two plots showing feature importance based on 'split' and 'gai

Output detailed information about the model Displays feature importance based on the coefficients of the LASSO model, showin

Show exception detail with QMessageBox.

Get raw data for a specific segment

Persist binding result via WechatEngine and refresh the UI.

Fit the model with dataset

Train the multi-layer perceptron model Trains the MLP model using the given dataset, with main steps including: 1. Preparing

Fit the model using the dataset Parameters ---------- dataset : AlphaDataset The dataset containing feat

Fit the model with dataset Parameters ---------- dataset : AlphaDataset The dataset used for training

Similar to math.floor function, but to target float number.

Forward propagation calculation Parameters ---------- x : torch.Tensor Input feature tensor, shape (batc

Functions to be run in genetic algorithm optimization.

Generate the bar data and call callback immediately.

return vt_symbol

Get latest account data by vt_accountid.

Get all account data.

Get all active quotes.

Get all daily profit and loss information

Get all order data.

Get all order information

Get all plot objects.

Get all position data.

Get all quote data.

Get all tick data.

Get all trade data.

Get all trade information

Return bar data avaible in database.

Legacy compatibility method

Get current available cash

Get offset converter object of specific gateway.

Return default setting dict.

Get current holding market value

Get information text to show by cursor.

Get information text to show by cursor.

Get latest order data by vt_orderid.

Get specific plot with its name.

Get total portfolio value

Get latest position data by vt_positionid.

Get latest quote data by vt_orderid.

Get model prediction signal for current time

Return tick data avaible in database.

Get trade data by vt_tradeid.

Get range of y-axis with given x-axis range. If min_ix and max_ix not specified, then return range with whole data set.

Get range of y-axis with given x-axis range. If min_ix and max_ix not specified, then return range with whole data set.

Return the maximum value between two features

Get high price time series.

Initialize datafeed service connection.

Connect signal.

Connect signal.

Initialize the build hook

Check if the quote is active.

Reimplement this method of parent to move chart horizontally and zoom in/out.

Return the minimum value between two features

List all datasets

List all models

List all signals

Load bar data from database.

Load bar data as DataFrame

Collect index component duration filters

Collect index component symbols

Load historical data

Load dataset

Load model

Load signal

Load tick data from database.

Calculate the natural logarithm of the feature

Get low price time series.

Account event push. Account event of a specific vt_accountid is also pushed.

K-line slice callback

Contract event push.

Strategy initialization callback

Order event push. Order event of a specific vt_orderid is also pushed.

Position event push. Position event of a specific vt_symbol is also pushed.

Quote event push. Quote event of a specific vt_symbol is also pushed.

Tick event push. Tick event of a specific vt_symbol is also pushed.

Trade event push. Trade event of a specific vt_symbol is also pushed.

Trade execution callback