У меня есть данные, подобные приведенному ниже образцу, в котором есть 4 непрерывных столбца [от x0 до x3] и двоичный столбец y. у имеет два значения 1,0 и 0,0. Я пытаюсь проверить корреляцию между двоичным столбцом y и одним из непрерывных столбцов x0, используя функцию CatConCor ниже, но я получаю сообщение об ошибке ниже. Функция создает модель линейной регрессии и вычисляет значение p для остатков с категориальной переменной и без нее. Если кто-то может указать на проблему или как ее исправить, она будет очень признательна.
Данные:
x_r x0 x1 x2 x3 y
0 0 0.466726 0.030126 0.998330 0.892770 0.0
1 1 0.173168 0.525810 -0.079341 -0.112151 0.0
2 2 -0.854467 0.770712 0.929614 -0.224779 0.0
3 3 -0.370574 0.568183 -0.928269 0.843253 0.0
4 4 -0.659431 -0.948491 -0.091534 0.706157 0.0
Код:
import numpy as np
import pandas as pd
from time import time
import scipy.stats as stats
from IPython.display import display # Allows the use of display() for DataFrames
# Pretty display for notebooks
%matplotlib inline
###########################################
# Suppress matplotlib user warnings
# Necessary for newer version of matplotlib
import warnings
warnings.filterwarnings("ignore", category = UserWarning, module = "matplotlib")
#
# Display inline matplotlib plots with IPython
from IPython import get_ipython
get_ipython().run_line_magic('matplotlib', 'inline')
###########################################
import matplotlib.pyplot as plt
import matplotlib.cm as cm
# correlation between categorical variable and continuous variable
def CatConCor(df,catVar,conVar):
import statsmodels.api as sm
from statsmodels.formula.api import ols
# subsetting data for one categorical column and one continuous column
data2=df.copy()[[catVar,conVar]]
data2[catVar]=data2[catVar].astype('category')
mod = ols(conVar+'~'+catVar,
data=data2).fit()
aov_table = sm.stats.anova_lm(mod, typ=2)
if aov_table['PR(>F)'][0] < 0.05:
print('Correlated p='+str(aov_table['PR(>F)'][0]))
else:
print('Uncorrelated p='+str(aov_table['PR(>F)'][0]))
# checking for correlation between categorical and continuous variables
CatConCor(df=train_df,catVar='y',conVar='x0')
Ошибка:
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-6-80f83b8c8e14> in <module>()
1 # checking for correlation between categorical and continuous variables
2
----> 3 CatConCor(df=train_df,catVar='y',conVar='x0')
<ipython-input-2-35404ba1d697> in CatConCor(df, catVar, conVar)
103
104 mod = ols(conVar+'~'+catVar,
--> 105 data=data2).fit()
106
107 aov_table = sm.stats.anova_lm(mod, typ=2)
~/anaconda2/envs/py36/lib/python3.6/site-packages/statsmodels/base/model.py in from_formula(cls, formula, data, subset, drop_cols, *args, **kwargs)
153
154 tmp = handle_formula_data(data, None, formula, depth=eval_env,
--> 155 missing=missing)
156 ((endog, exog), missing_idx, design_info) = tmp
157
~/anaconda2/envs/py36/lib/python3.6/site-packages/statsmodels/formula/formulatools.py in handle_formula_data(Y, X, formula, depth, missing)
63 if data_util._is_using_pandas(Y, None):
64 result = dmatrices(formula, Y, depth, return_type='dataframe',
---> 65 NA_action=na_action)
66 else:
67 result = dmatrices(formula, Y, depth, return_type='dataframe',
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/highlevel.py in dmatrices(formula_like, data, eval_env, NA_action, return_type)
308 eval_env = EvalEnvironment.capture(eval_env, reference=1)
309 (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env,
--> 310 NA_action, return_type)
311 if lhs.shape[1] == 0:
312 raise PatsyError("model is missing required outcome variables")
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/highlevel.py in _do_highlevel_design(formula_like, data, eval_env, NA_action, return_type)
163 return iter([data])
164 design_infos = _try_incr_builders(formula_like, data_iter_maker, eval_env,
--> 165 NA_action)
166 if design_infos is not None:
167 return build_design_matrices(design_infos, data,
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/highlevel.py in _try_incr_builders(formula_like, data_iter_maker, eval_env, NA_action)
60 "ascii-only, or else upgrade to Python 3.")
61 if isinstance(formula_like, str):
---> 62 formula_like = ModelDesc.from_formula(formula_like)
63 # fallthrough
64 if isinstance(formula_like, ModelDesc):
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/desc.py in from_formula(cls, tree_or_string)
162 tree = tree_or_string
163 else:
--> 164 tree = parse_formula(tree_or_string)
165 value = Evaluator().eval(tree, require_evalexpr=False)
166 assert isinstance(value, cls)
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/parse_formula.py in parse_formula(code, extra_operators)
146 tree = infix_parse(_tokenize_formula(code, operator_strings),
147 operators,
--> 148 _atomic_token_types)
149 if not isinstance(tree, ParseNode) or tree.type != "~":
150 tree = ParseNode("~", None, [tree], tree.origin)
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/infix_parser.py in infix_parse(tokens, operators, atomic_types, trace)
208
209 want_noun = True
--> 210 for token in token_source:
211 if c.trace:
212 print("Reading next token (want_noun=%r)" % (want_noun,))
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/parse_formula.py in _tokenize_formula(code, operator_strings)
92 else:
93 it.push_back((pytype, token_string, origin))
---> 94 yield _read_python_expr(it, end_tokens)
95
96 def test__tokenize_formula():
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/parse_formula.py in _read_python_expr(it, end_tokens)
42 origins = []
43 bracket_level = 0
---> 44 for pytype, token_string, origin in it:
45 assert bracket_level >= 0
46 if bracket_level == 0 and token_string in end_tokens:
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/util.py in next(self)
330 else:
331 # May raise StopIteration
--> 332 return six.advance_iterator(self._it)
333 __next__ = next
334
~/anaconda2/envs/py36/lib/python3.6/site-packages/patsy/tokens.py in python_tokenize(code)
33 break
34 origin = Origin(code, start, end)
---> 35 assert pytype not in (tokenize.NL, tokenize.NEWLINE)
36 if pytype == tokenize.ERRORTOKEN:
37 raise PatsyError("error tokenizing input "
AssertionError: