TDA_Prediction.py

def dataload():
    """
    upload toy datasets from scikit-learn
    """
    data = None
    return data

def datafetch(file_name):
    """
    upload real world datasets from scikit-learn
    """
    data = None
    print("reading data from:", file_name)
    return data

def descriptive_statistic(df):
    """
    Provides brief descriptive statistics on dataset. 
    Takes dataframe as input.
    """
    print("Type : ", None, "\n\n")
    print("Shape : ", None)
    print("Head -- \n", None)
    print("\n\n Tail -- \n", None)
    print("Describe : ", None)
    
def model_selection(df):
    """
    Takes dateframe as input. Performs foward/backward stepwise
    regression. Returns best model for both methods.
    """
    null_fit = None
    foward_step = None
    backward_step = None
    return foward_step, backward_step

def MSE_fit(fit): 
    """
    Takes in a fitted model as the input.
    Calculates the MSU of the fitted model.
    Outputs the model's MSE.
    """
    MSE = None
    return MSE

def accuracy_metrics(fit, MSE):
    """
    This function is used for model validation. It returns a dictionary
    of several regression model accuracy metrics. Its inputs are a fitted model
    and the MSE of the fitted model.
    """
    d = dict()
    sumObj = None
    SSE = None
    n = None
    p = None
    pr = None
    d['R2'] = None
    d['R2ad'] = None
    d['AIC'] = None
    d['BIC'] = None
    d['PRESS'] = None
    d['Cp']= None
    return d