Getting error 'int' object has no attribute 'encode' with rpy2

[sailinz]

I'm trying to use this library in the Jupyter notebook. The library can be successfully imported after the R_Home is changed as:

os.environ['R_HOME'] = "/Library/Frameworks/R.framework/Resources

However, when I try to test with the example code, I encounter the below error: ` Traceback (most recent call last): File "testPCA.py", line 16, in varimax_pca5 = CustomPCA(n_components=5, rotation='varimax').fit(X_std) File "~/lib/python3.7/site-packages/sklearn/decomposition/_pca.py", line 351, in fit self._fit(X) File "~/lib/python3.7/site-packages/advanced_pca/custom_pca.py", line 182, in _fit rot_factor_matrix = self._varimax(pd.DataFrame(factor_matrix)) File "~/lib/python3.7/site-packages/advanced_pca/custom_pca.py", line 125, in _varimax factor_mtr = self._df2mtr(factor_df) File "~/lib/python3.7/site-packages/advanced_pca/custom_pca.py", line 107, in _df2mtr rlc.OrdDict([('index', StrVector(tuple(df.index))), File "~/lib/python3.7/site-packages/rpy2/robjects/vectors.py", line 385, in init super().init(obj) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py", line 512, in init super().init(self.from_object(obj).sexp) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py", line 592, in from_object res = cls.from_iterable(obj) File "~/lib/python3.7/site-packages/rpy2/rinterfacelib/conversion.py", line 44, in cdata = function(*args, **kwargs) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py", line 541, in from_iterable populate_func(iterable, r_vector, set_elt, cast_value) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py", line 463, in _populate_r_vector set_elt(r_vector, i, cast_value(v)) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py", line 655, in _as_charsxp_cdata return conversion._str_to_charsxp(x) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/conversion.py", line 139, in _str_to_charsxp cchar = _str_to_cchar(val) File "~/lib/python3.7/site-packages/rpy2/rinterface_lib/conversion.py", line 118, in _str_to_cchar b = s.encode(encoding) AttributeError: 'int' object has no attribute 'encode'

`

Any ideas on this?

[jkuruzovich]

I'm getting this same error.

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in from_object(cls, obj)
    587         try:
--> 588             mv = memoryview(obj)
    589             res = cls.from_memoryview(mv)

TypeError: memoryview: a bytes-like object is required, not 'tuple'

During handling of the above exception, another exception occurred:

AttributeError                            Traceback (most recent call last)
<ipython-input-127-abd45db94e07> in <module>
     10 # fit pca objects with and without rotation with 5 principal components
     11 standard_pca5 = CustomPCA(n_components=5).fit(X_std)
---> 12 varimax_pca5 = CustomPCA(n_components=5, rotation='varimax').fit(X_std)

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/sklearn/decomposition/pca.py in fit(self, X, y)
    339             Returns the instance itself.
    340         """
--> 341         self._fit(X)
    342         return self
    343 

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/advanced_pca/custom_pca.py in _fit(self, X)
    180                 )
    181 
--> 182                 rot_factor_matrix = self._varimax(pd.DataFrame(factor_matrix))
    183 
    184                 self.explained_variance_ = (rot_factor_matrix ** 2).sum(axis=0)

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/advanced_pca/custom_pca.py in _varimax(self, factor_df, **kwargs)
    123             rot_factor_df: rotated factor matrix as pd.DataFrame
    124         '''
--> 125         factor_mtr = self._df2mtr(factor_df)
    126         varimax = robjects.r['varimax']
    127         rot_factor_mtr = varimax(factor_mtr)

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/advanced_pca/custom_pca.py in _df2mtr(df)
    105         values = FloatVector(df.values.flatten())
    106         dimnames = ListVector(
--> 107             rlc.OrdDict([('index', StrVector(tuple(df.index))),
    108             ('columns', StrVector(tuple(df.columns)))])
    109         )

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/robjects/vectors.py in __init__(self, obj)
    383 
    384     def __init__(self, obj):
--> 385         super().__init__(obj)
    386         self._add_rops()
    387 

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in __init__(self, obj)
    510             super().__init__(obj)
    511         elif isinstance(obj, collections.abc.Sized):
--> 512             super().__init__(self.from_object(obj).__sexp__)
    513         else:
    514             raise TypeError('The constructor must be called '

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in from_object(cls, obj)
    590         except (TypeError, ValueError):
    591             try:
--> 592                 res = cls.from_iterable(obj)
    593             except ValueError:
    594                 msg = ('The class methods from_memoryview() and '

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/conversion.py in _(*args, **kwargs)
     42 def _cdata_res_to_rinterface(function):
     43     def _(*args, **kwargs):
---> 44         cdata = function(*args, **kwargs)
     45         # TODO: test cdata is of the expected CType
     46         return _cdata_to_rinterface(cdata)

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in from_iterable(cls, iterable, populate_func, set_elt, cast_value)
    539                     cls._R_TYPE, n)
    540             )
--> 541             populate_func(iterable, r_vector, set_elt, cast_value)
    542         return r_vector
    543 

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in _populate_r_vector(iterable, r_vector, set_elt, cast_value)
    461 def _populate_r_vector(iterable, r_vector, set_elt, cast_value):
    462     for i, v in enumerate(iterable):
--> 463         set_elt(r_vector, i, cast_value(v))
    464 
    465 

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/sexp.py in _as_charsxp_cdata(x)
    653         return x.__sexp__._cdata
    654     else:
--> 655         return conversion._str_to_charsxp(x)
    656 
    657 

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/conversion.py in _str_to_charsxp(val)
    137         s = rlib.R_NaString
    138     else:
--> 139         cchar = _str_to_cchar(val)
    140         s = rlib.Rf_mkCharCE(cchar, _CE_DEFAULT_VALUE)
    141     return s

~/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/rpy2/rinterface_lib/conversion.py in _str_to_cchar(s, encoding)
    116 def _str_to_cchar(s: str, encoding: str = 'utf-8'):
    117     # TODO: use isStrinb and installTrChar
--> 118     b = s.encode(encoding)
    119     return ffi.new('char[]', b)
    120 

AttributeError: 'int' object has no attribute 'encode'```

[alfredsasko]

It seems that code is broken in custom method transforming pandas dataframe to r matrix. Let me know which version of rpy2 are you using that I can simulate it.

[sailinz]

Thank you for looking into this. My rp2 is installed via Anaconda. The version is 3.3.3.

It seems that code is broken in custom method transforming pandas dataframe to r matrix. Let me know which version of rpy2 are you using that I can simulate it.

[tenggaard]

I am getting the same error with rpy2-3.3.5

[claudiomartelli]

I have the same problem with rpy2 ver 3.3.6

I solved changing code in custom_pca.py as follow:

def _df2mtr(df):
    '''Convert pandas dataframe to r matrix. Category dtype is casted as
    factorVector considering missing values
    (original py2ri function of rpy2 can't handle this properly so far)

    Args:
        data: pandas dataframe of shape (# samples, # features)
              with numeric dtype

    Returns:
        mtr: r matrix of shape (# samples # features)
    '''
    # check arguments
    assert isinstance(df, pd.DataFrame), 'Argument df need to be a pd.Dataframe.'

    # select only numeric columns
    df = df.select_dtypes('number')

    # create and return r matrix
    values = FloatVector(df.values.flatten())
    dimnames = ListVector(
        rlc.OrdDict([('index', StrVector(tuple(str(x) for x in df.index))),
        ('columns', StrVector(tuple(str(x) for x in df.columns)))])
    )

    return robjects.r.matrix(values, nrow=len(df.index), ncol=len(df.columns),
                             dimnames = dimnames, byrow=True)

def _varimax(self, factor_df, **kwargs):
    '''
    varimax rotation of factor matrix

    Args:
        factor_df: factor matrix as pd.DataFrame with shape
                   (# features, # principal components)

    Return:
        rot_factor_df: rotated factor matrix as pd.DataFrame
    '''
    factor_mtr = self._df2mtr(factor_df)
    varimax = robjects.r['varimax']
    rot_factor_mtr = varimax(factor_mtr)
    return pandas2ri.rpy2py(rot_factor_mtr.rx2('loadings'))

[ptgoff]

Are your changes reflected in the latest version? I downloaded (via pip) this week and I'm running into the same issue.