def __bestks_bin(self, single_series, y):
df_input = _Basic.basic_prepare(y, self.good, self.bad)
self.kwargs['df_'] = pd.DataFrame(y)
self.kwargs['response'] = y.name
part_, single_series, special = CutMethods.cut_method_flow(
single_series, **self.kwargs)
uncheck_len = 2 if self.strict_monotonicity else 3 # 严格单调性
arrays = []
for group in part_:
if len(group) < 2: # 用于special存在的情况
arrays.append(group)
elif len(group) <= uncheck_len:
if _Basic.check_proportion(single_series, group, self.kwargs):
arrays.append(group)
else:
try: # 只检测了单调性，可以增加检测分组的数量,增加个参数每个组至少0.05
if _Basic.check_proportion(single_series, group,
self.kwargs):
tmp_woe = _Basic.get_tmp_woe(df_input, single_series,
group, y.name,
self.kwargs)
if _Basic.check_monotonic(tmp_woe, self.kwargs):
arrays.append(group)
except KeyError as error:
logging.error(error)
ivs = 0
df_last = None
cut_last = []
if not arrays:
return False
for array in arrays:
if special[0]: # 将特殊点加进去
if special[1] == 0.01:
array[0] = special[0] + special[1]
array.append(special[0])
array.sort()
df_input_tmp = copy.deepcopy(df_input)
out = pd.cut(single_series, array,
include_lowest=True) # 只留下符合单调的切分后重新切分得到结果
out = out.cat.add_categories([self.fill_value
]).fillna(self.fill_value)
out = out.cat.remove_unused_categories()
df_input_tmp[single_series.name] = out
df_input_tmp = _Basic.get_pivot_table(df_input_tmp, y.name,
single_series.name)
df_input_tmp = _Basic.add_basic_info_to_df(df_input_tmp)
df_input_tmp = _Basic.add_woe_iv_to_df(df_input_tmp)
# 上面都是重复之前的操作
df_output = _Basic.add_ks_to_df(df_input_tmp)
iv_sum = df_output["IV"].sum()
if ivs < iv_sum:
cut_last = array
ivs = iv_sum
df_last = copy.deepcopy(df_output)
df_last.sort_index(inplace=True)
return cut_last, df_last
def get_sample_bestks(df_, test):
kwargs["cut_method"] = "bestks"
print "*****************************{0}**************************************".format(
kwargs["cut_method"])
part_, test = _CutMethods.cut_method_flow(test,
kwargs,
response="code",
df_=df_)
# groups为切割的组合，后面进行排列组合计算iv的值
df_input = _Basic.basic_prepare(df_["code"], kwargs["good"], kwargs["bad"])
uncheck_len = 4
if kwargs["strict_monotonicity"]: # 严格单调性
uncheck_len = 3
arrays = []
for group in part_:
if len(group) <= uncheck_len:
if _Basic.check_proportion(test, group, kwargs):
arrays.append(group)
else:
try: # 只检测了单调性，可以增加检测分组的数量,增加个参数每个组至少0.05
if _Basic.check_proportion(test, group, kwargs):
tmp_woe = _Basic.get_tmp_woe(df_input, test, group, "code",
kwargs)
if _Basic.check_monotonic(tmp_woe, kwargs):
arrays.append(group)
except KeyError as error:
logging.error(error)
# 筛选出符合单调的要求和分布要求的,再筛选出iv最大的一个
ivs = 0
df_last = None
for array in arrays:
df_input_tmp = copy.deepcopy(df_input)
out = pd.cut(test, array, include_lowest=True) # 只留下符合单调的切分后重新切分得到结果
out = out.cat.add_categories([kwargs["fill_value"]
]).fillna(kwargs["fill_value"])
out = out.cat.remove_unused_categories()
df_input_tmp["test"] = out
df_input_tmp = _Basic.get_pivot_table(df_input_tmp, "code", "test")
df_input_tmp = _Basic.add_basic_info_to_df(df_input_tmp)
df_input_tmp = _Basic.add_woe_iv_to_df(df_input_tmp)
# 上面都是重复之前的操作
df_output = _Basic.add_ks_to_df(df_input_tmp)
iv_sum = df_output["IV"].sum()
# print df_output
if ivs < iv_sum:
ivs = iv_sum
df_last = copy.deepcopy(df_output)
print df_last
print "*****************************{0}**************************************".format(
kwargs["cut_method"])
def __general_bin(self, single_series, y):
array = []
df_input = _Basic.basic_prepare(y, self.good, self.bad)
part_, single_series, special = CutMethods.cut_method_flow(
single_series, **self.kwargs)
uncheck_len = 2 if self.strict_monotonicity else 3 # 严格单调性
for group in part_:
if len(group) < 2: # 用于special存在的情况
array.append(group)
elif len(group) <= uncheck_len:
if _Basic.check_proportion(single_series, group, self.kwargs):
array.append(group)
else:
try: # 只检测了单调性，可以增加检测分组的数量,增加个参数每个组至少0.05
if _Basic.check_proportion(single_series, group,
self.kwargs):
tmp_woe = _Basic.get_tmp_woe(df_input, single_series,
group, y.name,
self.kwargs)
if _Basic.check_monotonic(tmp_woe, self.kwargs):
array.append(group)
except KeyError as error:
logging.error(error)
if not array:
return False
cut_points = array[-1]
if special[0]: # 将特殊点加进去
if special[1] == 0.01:
cut_points[0] = special[0] + special[1]
cut_points.append(special[0])
cut_points.sort()
out = pd.cut(single_series, cut_points,
include_lowest=True) # 只留下符合单调的切分后重新切分得到结果
out = out.cat.add_categories([self.fill_value]).fillna(self.fill_value)
out = out.cat.remove_unused_categories()
df_input[single_series.name] = out
df_input = _Basic.get_pivot_table(df_input, y.name, single_series.name)
df_input = _Basic.add_basic_info_to_df(df_input)
df_input = _Basic.add_woe_iv_to_df(df_input)
# 上面都是重复之前的操作
df_output = _Basic.add_ks_to_df(df_input)
df_output.sort_index(inplace=True)
return cut_points, df_output
def get_sample(df_, test):
kwargs["cut_method"] = "quantile"
print "*****************************{0}**************************************".format(
kwargs["cut_method"])
df_input = _Basic.basic_prepare(df_["code"], kwargs["good"], kwargs["bad"])
array = []
part_, test = _CutMethods.cut_method_flow(test, kwargs)
# part_各个分位数的值,test原始数据
uncheck_len = 4
if kwargs["strict_monotonicity"]: # 严格单调性
uncheck_len = 3
for group in part_:
if len(group) <= uncheck_len:
if _Basic.check_proportion(test, group, kwargs):
array.append(group)
else:
try: # 只检测了单调性，可以增加检测分组的数量,增加个参数每个组至少0.05
if _Basic.check_proportion(test, group, kwargs):
tmp_woe = _Basic.get_tmp_woe(df_input, test, group, "code",
kwargs)
if _Basic.check_monotonic(tmp_woe, kwargs):
array.append(group)
# else:
# break
# else: # 不满足单调舍弃
# break
except KeyError as error:
logging.error(error)
print(array)
out = pd.cut(test, array[-1], include_lowest=True) # 只留下符合单调的切分后重新切分得到结果
out = out.cat.add_categories([kwargs["fill_value"]
]).fillna(kwargs["fill_value"])
out = out.cat.remove_unused_categories()
df_input["test"] = out
df_input = _Basic.get_pivot_table(df_input, "code", "test")
df_input = _Basic.add_basic_info_to_df(df_input)
df_input = _Basic.add_woe_iv_to_df(df_input)
# 上面都是重复之前的操作
df_output = _Basic.add_ks_to_df(df_input)
print df_output
print "*****************************{0}**************************************".format(
kwargs["cut_method"])