dowhy/utils/dgps/cubic_dgp.py [13:32]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.auto_gen = False

        if self.weights == {} and self.bias == {}:
            self.auto_gen = True

    def generate_data(self, sample_size):
        self.weights = {}
        self.bias = {}
        weights = []
        bias = []
        treatment = []
        outcome = []
        y_treatment = []
        y_control = []
        confounder = np.random.randn(sample_size, len(self.confounder))
        effect_modifier = np.random.randn(sample_size, len(self.effect_modifier))
        control_value = np.zeros( (sample_size, len(self.treatment) ) )
        treatment_value = np.ones( (sample_size, len(self.treatment) ) )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



dowhy/utils/dgps/quadratic_dgp.py [13:32]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.auto_gen = False

        if self.weights == {} and self.bias == {}:
            self.auto_gen = True

    def generate_data(self, sample_size):
        self.weights = {}
        self.bias = {}
        weights = []
        bias = []
        treatment = []
        outcome = []
        y_treatment = []
        y_control = []
        confounder = np.random.randn(sample_size, len(self.confounder))
        effect_modifier = np.random.randn(sample_size, len(self.effect_modifier))
        control_value = np.zeros( (sample_size, len(self.treatment) ) )
        treatment_value = np.ones( (sample_size, len(self.treatment) ) )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -