1.等宽分箱
# ===========================方法一===============================
def binnings(data_res, b_for_filename):
a = 'bins_by' # 分箱依据
b = 'used_to_count' # 分箱之后用来统计数量的字段
test_result_out = data_res[[b, a]]
test_result_out['score'] = [int(i) for i in test_result_out[a]]
# 分箱
test_result_out['bin'] = pd.cut(list(test_result_out['score']), [i for i in range(300, 960, 30)])
test_result_out['bin'] = test_result_out['bin'].astype(np.str)
test_result_out['bin'] = test_result_out['bin'].replace('nan', -999) # 空值处理
# 分箱之后的处理
bins = test_result_out.groupby('bin', as_index=False).count()[['bin', b]]
# bins[b].sum()
bins['rate'] = bins[b]/bins[b].sum()
bins.columns = ['bin', 'count', 'percentage']
bins['percentage'] = [round(i, 3) for i in bins['percentage']] # 分箱之后的每个箱子所占百分比
# 保存
bins.to_excel('save_path/test_'+a+'_'+b_for_filename+'_bins.xlsx', index=False)
# ====