def __init__(self, data=None, name='regression', formula=None, var_transform=False, *args, **kwargs):
super().__init__(data=data, name=name, *args, **kwargs)
# 创建REnv实例
self._renv = REnv()
# 创建公式
self._formula = formula
# 原始公式
self._origin_formula = self._formula
self._copy_data = deepcopy(data)
# 转换变量，特别是那些变量是中文的
self._var_transform = var_transform
if self._var_transform:
self._variables_mapping = [(self._copy_data.columns[i],'_'.join(['var',str(i)]))
for i in range(len(self._copy_data.columns))]
self._variables_mapping_dict = dict(self._variables_mapping)
self._variables_mapping_dict_reversed = dict([('_'.join(['var',str(i)]),self._copy_data.columns[i]) for i in range(len(self._copy_data.columns))])
self._generated_variables = [item[1] for item in self._variables_mapping]
self._copy_data.columns = self._generated_variables
for key in self._variables_mapping_dict:
self._formula = re.sub(key,self._variables_mapping_dict[key],self._formula)
self._formula = Formula(self._formula)
self._lm = importr('stats').lm
self._summary = importr('base').summary
def __init__(self, data=None, name='Propensity Score Matching', formula=None, method='nearest',
distance = 'logit', var_transform=False, *args, **kwargs):
super().__init__(data=data, name=name, *args, **kwargs)
# 创建REnv实例
self._renv = REnv()
# 创建matchit
self._formula = formula
# 创建方法
self._method = method
# 创建距离
self._distance = distance
# 原始公式
self._origin_formula = self._formula
self._copy_data = deepcopy(data)
# 转换变量，特别是那些变量是中文的
self._var_transform = var_transform
if self._var_transform:
self._variables_mapping = [(self._copy_data.columns[i],'_'.join(['var',str(i)]))
for i in range(len(self._copy_data.columns))]
self._variables_mapping_dict = dict(self._variables_mapping)
self._variables_mapping_dict_reversed = dict([('_'.join(['var',str(i)]),self._copy_data.columns[i]) for i in range(len(self._copy_data.columns))])
self._generated_variables = [item[1] for item in self._variables_mapping]
self._copy_data.columns = self._generated_variables
for key in self._variables_mapping_dict:
self._formula = re.sub(key,self._variables_mapping_dict[key],self._formula)
# self._formula = Formula(self._formula)
# 导入MatchIt库
self._renv._R.r('library("MatchIt")')
# 把数据转换为R数据格式
self._renv['mdata'] = self._renv.python_to_r_object(self._copy_data)
self._summary = importr('base').summary
def __init__(self,
data=None,
id=None,
time=None,
name='panel data model',
formula=None,
var_transform=False,
model='Fixed',
*args,
**kwargs):
super().__init__(data=data, name=name, *args, **kwargs)
# 创建REnv实例
self._renv = REnv()
# 创建公式
self._formula = formula
# 原始公式
self._origin_formula = self._formula
self._copy_data = deepcopy(data)
# 转换变量，特别是那些变量是中文的
self._var_transform = var_transform
if self._var_transform:
self._variables_mapping = [
(self._copy_data.columns[i], '_'.join(['var', str(i)]))
for i in range(len(self._copy_data.columns))
]
self._variables_mapping_dict = dict(self._variables_mapping)
self._variables_mapping_dict_reversed = dict([
('_'.join(['var', str(i)]), self._copy_data.columns[i])
for i in range(len(self._copy_data.columns))
])
self._generated_variables = [
item[1] for item in self._variables_mapping
]
self._copy_data.columns = self._generated_variables
for key in self._variables_mapping_dict:
self._formula = re.sub(key, self._variables_mapping_dict[key],
self._formula)
#self._formula = Formula(self._formula)
self._model = model
# 导入plm库
self._renv._R.r('library("plm")')
# 把数据转换为R数据格式
self._renv['mdata'] = self._renv.python_to_r_object(self._copy_data)
# 把数据格式转换为面板格式
fmt_str = 'pdata <- pdata.frame(mdata, index=c("{0}","{1}"))'
self._renv._R.r(fmt_str.format(id, time))
self._summary = importr('base').summary
def __init__(self,
data=None,
name='Propensity Score Matching',
formula=None,
method='nearest',
distance='logit',
var_transform=False,
*args,
**kwargs):
super().__init__(data=data, name=name, *args, **kwargs)
# 创建REnv实例
self._renv = REnv()
# 创建matchit
self._formula = formula
# 创建方法
self._method = method
# 创建距离
self._distance = distance
# 原始公式
self._origin_formula = self._formula
self._copy_data = deepcopy(data)
# 转换变量，特别是那些变量是中文的
self._var_transform = var_transform
if self._var_transform:
self._variables_mapping = [
(self._copy_data.columns[i], '_'.join(['var', str(i)]))
for i in range(len(self._copy_data.columns))
]
self._variables_mapping_dict = dict(self._variables_mapping)
self._variables_mapping_dict_reversed = dict([
('_'.join(['var', str(i)]), self._copy_data.columns[i])
for i in range(len(self._copy_data.columns))
])
self._generated_variables = [
item[1] for item in self._variables_mapping
]
self._copy_data.columns = self._generated_variables
for key in self._variables_mapping_dict:
self._formula = re.sub(key, self._variables_mapping_dict[key],
self._formula)
# self._formula = Formula(self._formula)
# 导入MatchIt库
self._renv._R.r('library("MatchIt")')
# 把数据转换为R数据格式
self._renv['mdata'] = self._renv.python_to_r_object(self._copy_data)
self._summary = importr('base').summary
'''
stata_file = r'D:\data\test\JTRAIN.dta'
stdata = Statadata(stata_file)
mdata = stdata.read()
print(mdata.columns)
plm = importr('plm')
reg_obj = Plm(data=mdata, formula='log(scrap)~d88+d89+grant+grant_1', id='fcode', time='year')
call_obj = reg_obj()
print(reg_obj.coefs)
print(reg_obj._result['summary']['coefficients'])
print(reg_obj)'''
stata_file = r'D:\data\test\wagepan.dta'
stdata = Statadata(stata_file)
mdata = stdata.read()
print(mdata.columns)
plm = importr('plm')
reg_obj = Plm(
data=mdata,
formula='lwage~educ+black+hisp+exper+I(exper^2)+married+union+yr',
id='nr',
time='year',
model='random')
reg_obj._renv._R.r('pdata$yr<-factor(pdata$year)')
call_obj = reg_obj()
print(reg_obj.coefs)
print(reg_obj._result['summary']['coefficients'])
print(reg_obj)