import pandas as pd
import numpy as np
import statistics

def create_dict(df, classColumnName):
    return dict(df[classColumnName].value_counts())

def remove_weak_classes(df, classColumnName, threshold):

    dictOfClassInstances = create_dict(df,classColumnName)


    dictionary = {k: v for k, v in dictOfClassInstances.items() if v >= threshold }
    keys = [*dictionary]
    df_tmp = df[~ df[classColumnName].isin(keys)]
    #df = df[df[columnTarget] not in keys]
    #df =  df.merge(df_tmp, how = 'outer' ,indicator=True)
    df =  pd.concat([df,df_tmp]).drop_duplicates(keep=False)
    return df



def split_class(df, columnProcessed):
    i = 0
    new_df = pd.DataFrame(columns= df.columns)
    for index, row in df.iterrows():
        #cls = re.split(';', row[columnProcessed])
        cls = filter(None, row[columnProcessed].split(';'))
        cls = list(cls)
        #cls = re.findall(r"[\w']+", row [columnProcessed])
        r = row
        for categ in cls:
            r[columnProcessed] = categ
            #new_df.append(r, ignore_index = True)
            new_df.loc[i] = r
            i = i + 1

    return new_df

def get_median_dict(dict):
    return statistics.median(dict.values())

def resample_classes(df, classColumnName, numberOfInstances):
    # numberOfInstances first elements
    #return df.groupby(classColumnName).apply(lambda x: x[:numberOfInstances][df.columns])
    #random numberOfInstances elements
    replace = False  # with replacement

    fn = lambda obj: obj.loc[np.random.choice(obj.index, numberOfInstances if len(obj) > numberOfInstances else len(obj), replace),:]
    return df.groupby(classColumnName, as_index=False).apply(fn)