mukundkal / pandas-cub Goto Github PK

def _add_docs(self):
        agg_names = ['min', 'max', 'mean', 'median', 'sum', 'var',
                     'std', 'any', 'all', 'argmax', 'argmin']
        agg_doc = \
        """
        Find the {} of each column
        
        Returns
        -------
        DataFrame
        """
        for name in agg_names:
            getattr(DataFrame, name).__doc__ = agg_doc.format(name)

def read_csv(fn):
    """
    Read in a comma-separated value file as a DataFrame

    Assume Header row is present.

    Parameters
    ----------
    fn: string of file location

    Returns
    -------
    A DataFrame
    """
    
    from collections import defualtdict

    data = defualtdict(list)

    with open(fn) as f:
    	header = f.readline() #comma separated string
    	column_names = header.split('\n').split(',') #column name list

    	for line in f:  #next line after header
			values = line.strip('\n').split(',')
			for col, val in zip(column_names,values):
				data[col].append(val)