casm.learn.TrainingData
- class casm.learn.TrainingData(input, verbose=True)[source]
TrainingData is a data structure used to collect data from the training data file.
- filename
The name of the training data file
- Type:
str
- filetype
The data format of the training data file
- Type:
str, one of [“selection”, “csv”, “json”]
- X_name
The name of the X columns in the training data file
- Type:
str
- X
The training input samples (correlations).
- Type:
array-like of shape (n_samples, n_features)
- y_name
The name of the y column in the training data file
- Type:
str
- y
The target values (property values).
- Type:
array-like of shape: (n_samples, 1)
- n_samples
The number of samples / target values (number of rows in X)
- Type:
int
- n_features
The number of features (number of columns in X)
- Type:
int
- sel
The selection specifying the training data
- Type:
casm.Selection, (exists if filetype==”selection”)
- data
Contains the X and y data
- Type:
pandas.DataFrame
- hull_dist_name
The name of the hull_dist column in the training data file
- Type:
str, (exists if weight method==”wHullDist”)
- hull_dist
The hull distance values.
- Type:
array-like of shape: (n_samples, 1), (exists if weight method==”wHullDist”)
- Parameters:
input (dict) – The input settings as a dict
verbose (boolean, optional, default=True) – Print information to stdout.
- __init__(input, verbose=True)[source]
- Parameters:
input (dict) – The input settings as a dict
verbose (boolean, optional, default=True) – Print information to stdout.
Methods
__init__(input[, verbose])- param input:
The input settings as a dict