rpy2 v2和v3之间有很多更改。我正在移植代码并修补一些兼容性问题。我不知道的一件事是如何使hclust工作。特别是从fastcluster包中获取，但我什至无法使基本hclust正常工作。
我不了解的几件事：（1）我应该使用R["as.dist"](rkernel)还是R("as.dist")(rkernel)？（2）当我在R中调用它时，为什么返回一个numpy数组？（3）如何使此相似对象与hclust和fastcluster::hclust一起使用？
我正在使用rpy2 v3.3.2 btw。
我正在使用与此类似的东西，但是它不再起作用了：feeding distance matrix to R clustering from Rpy2
import pandas as pd
import numpy as np
from rpy2 import robjects as ro
from rpy2 import rinterface as ri
from rpy2.robjects.packages import importr
R = ro.r
# r_stats = importr("stats")
fastcluster = importr("fastcluster")
def pandas_to_rpy2(df):
return ro.conversion.py2rpy(df)
def rpy2_to_pandas(r_df):
return ro.conversion.rpy2py(r_df)
# Data
X_iris = pd.DataFrame({'sepal_length': {'iris_0': 5.1, 'iris_1': 4.9, 'iris_2': 4.7, 'iris_3': 4.6, 'iris_4': 5.0, 'iris_5': 5.4, 'iris_6': 4.6, 'iris_7': 5.0, 'iris_8': 4.4, 'iris_9': 4.9, 'iris_10': 5.4, 'iris_11': 4.8, 'iris_12': 4.8, 'iris_13': 4.3, 'iris_14': 5.8, 'iris_15': 5.7, 'iris_16': 5.4, 'iris_17': 5.1, 'iris_18': 5.7, 'iris_19': 5.1, 'iris_20': 5.4, 'iris_21': 5.1, 'iris_22': 4.6, 'iris_23': 5.1, 'iris_24': 4.8, 'iris_25': 5.0, 'iris_26': 5.0, 'iris_27': 5.2, 'iris_28': 5.2, 'iris_29': 4.7, 'iris_30': 4.8, 'iris_31': 5.4, 'iris_32': 5.2, 'iris_33': 5.5, 'iris_34': 4.9, 'iris_35': 5.0, 'iris_36': 5.5, 'iris_37': 4.9, 'iris_38': 4.4, 'iris_39': 5.1, 'iris_40': 5.0, 'iris_41': 4.5, 'iris_42': 4.4, 'iris_43': 5.0, 'iris_44': 5.1, 'iris_45': 4.8, 'iris_46': 5.1, 'iris_47': 4.6, 'iris_48': 5.3, 'iris_49': 5.0, 'iris_50': 7.0, 'iris_51': 6.4, 'iris_52': 6.9, 'iris_53': 5.5, 'iris_54': 6.5, 'iris_55': 5.7, 'iris_56': 6.3, 'iris_57': 4.9, 'iris_58': 6.6, 'iris_59': 5.2, 'iris_60': 5.0, 'iris_61': 5.9, 'iris_62': 6.0, 'iris_63': 6.1, 'iris_64': 5.6, 'iris_65': 6.7, 'iris_66': 5.6, 'iris_67': 5.8, 'iris_68': 6.2, 'iris_69': 5.6, 'iris_70': 5.9, 'iris_71': 6.1, 'iris_72': 6.3, 'iris_73': 6.1, 'iris_74': 6.4, 'iris_75': 6.6, 'iris_76': 6.8, 'iris_77': 6.7, 'iris_78': 6.0, 'iris_79': 5.7, 'iris_80': 5.5, 'iris_81': 5.5, 'iris_82': 5.8, 'iris_83': 6.0, 'iris_84': 5.4, 'iris_85': 6.0, 'iris_86': 6.7, 'iris_87': 6.3, 'iris_88': 5.6, 'iris_89': 5.5, 'iris_90': 5.5, 'iris_91': 6.1, 'iris_92': 5.8, 'iris_93': 5.0, 'iris_94': 5.6, 'iris_95': 5.7, 'iris_96': 5.7, 'iris_97': 6.2, 'iris_98': 5.1, 'iris_99': 5.7, 'iris_100': 6.3, 'iris_101': 5.8, 'iris_102': 7.1, 'iris_103': 6.3, 'iris_104': 6.5, 'iris_105': 7.6, 'iris_106': 4.9, 'iris_107': 7.3, 'iris_108': 6.7, 'iris_109': 7.2, 'iris_110': 6.5, 'iris_111': 6.4, 'iris_112': 6.8, 'iris_113': 5.7, 'iris_114': 5.8, 'iris_115': 6.4, 'iris_116': 6.5, 'iris_117': 7.7, 'iris_118': 7.7, 'iris_119': 6.0, 'iris_120': 6.9, 'iris_121': 5.6, 'iris_122': 7.7, 'iris_123': 6.3, 'iris_124': 6.7, 'iris_125': 7.2, 'iris_126': 6.2, 'iris_127': 6.1, 'iris_128': 6.4, 'iris_129': 7.2, 'iris_130': 7.4, 'iris_131': 7.9, 'iris_132': 6.4, 'iris_133': 6.3, 'iris_134': 6.1, 'iris_135': 7.7, 'iris_136': 6.3, 'iris_137': 6.4, 'iris_138': 6.0, 'iris_139': 6.9, 'iris_140': 6.7, 'iris_141': 6.9, 'iris_142': 5.8, 'iris_143': 6.8, 'iris_144': 6.7, 'iris_145': 6.7, 'iris_146': 6.3, 'iris_147': 6.5, 'iris_148': 6.2, 'iris_149': 5.9}, 'sepal_width': {'iris_0': 3.5, 'iris_1': 3.0, 'iris_2': 3.2, 'iris_3': 3.1, 'iris_4': 3.6, 'iris_5': 3.9, 'iris_6': 3.4, 'iris_7': 3.4, 'iris_8': 2.9, 'iris_9': 3.1, 'iris_10': 3.7, 'iris_11': 3.4, 'iris_12': 3.0, 'iris_13': 3.0, 'iris_14': 4.0, 'iris_15': 4.4, 'iris_16': 3.9, 'iris_17': 3.5, 'iris_18': 3.8, 'iris_19': 3.8, 'iris_20': 3.4, 'iris_21': 3.7, 'iris_22': 3.6, 'iris_23': 3.3, 'iris_24': 3.4, 'iris_25': 3.0, 'iris_26': 3.4, 'iris_27': 3.5, 'iris_28': 3.4, 'iris_29': 3.2, 'iris_30': 3.1, 'iris_31': 3.4, 'iris_32': 4.1, 'iris_33': 4.2, 'iris_34': 3.1, 'iris_35': 3.2, 'iris_36': 3.5, 'iris_37': 3.6, 'iris_38': 3.0, 'iris_39': 3.4, 'iris_40': 3.5, 'iris_41': 2.3, 'iris_42': 3.2, 'iris_43': 3.5, 'iris_44': 3.8, 'iris_45': 3.0, 'iris_46': 3.8, 'iris_47': 3.2, 'iris_48': 3.7, 'iris_49': 3.3, 'iris_50': 3.2, 'iris_51': 3.2, 'iris_52': 3.1, 'iris_53': 2.3, 'iris_54': 2.8, 'iris_55': 2.8, 'iris_56': 3.3, 'iris_57': 2.4, 'iris_58': 2.9, 'iris_59': 2.7, 'iris_60': 2.0, 'iris_61': 3.0, 'iris_62': 2.2, 'iris_63': 2.9, 'iris_64': 2.9, 'iris_65': 3.1, 'iris_66': 3.0, 'iris_67': 2.7, 'iris_68': 2.2, 'iris_69': 2.5, 'iris_70': 3.2, 'iris_71': 2.8, 'iris_72': 2.5, 'iris_73': 2.8, 'iris_74': 2.9, 'iris_75': 3.0, 'iris_76': 2.8, 'iris_77': 3.0, 'iris_78': 2.9, 'iris_79': 2.6, 'iris_80': 2.4, 'iris_81': 2.4, 'iris_82': 2.7, 'iris_83': 2.7, 'iris_84': 3.0, 'iris_85': 3.4, 'iris_86': 3.1, 'iris_87': 2.3, 'iris_88': 3.0, 'iris_89': 2.5, 'iris_90': 2.6, 'iris_91': 3.0, 'iris_92': 2.6, 'iris_93': 2.3, 'iris_94': 2.7, 'iris_95': 3.0, 'iris_96': 2.9, 'iris_97': 2.9, 'iris_98': 2.5, 'iris_99': 2.8, 'iris_100': 3.3, 'iris_101': 2.7, 'iris_102': 3.0, 'iris_103': 2.9, 'iris_104': 3.0, 'iris_105': 3.0, 'iris_106': 2.5, 'iris_107': 2.9, 'iris_108': 2.5, 'iris_109': 3.6, 'iris_110': 3.2, 'iris_111': 2.7, 'iris_112': 3.0, 'iris_113': 2.5, 'iris_114': 2.8, 'iris_115': 3.2, 'iris_116': 3.0, 'iris_117': 3.8, 'iris_118': 2.6, 'iris_119': 2.2, 'iris_120': 3.2, 'iris_121': 2.8, 'iris_122': 2.8, 'iris_123': 2.7, 'iris_124': 3.3, 'iris_125': 3.2, 'iris_126': 2.8, 'iris_127': 3.0, 'iris_128': 2.8, 'iris_129': 3.0, 'iris_130': 2.8, 'iris_131': 3.8, 'iris_132': 2.8, 'iris_133': 2.8, 'iris_134': 2.6, 'iris_135': 3.0, 'iris_136': 3.4, 'iris_137': 3.1, 'iris_138': 3.0, 'iris_139': 3.1, 'iris_140': 3.1, 'iris_141': 3.1, 'iris_142': 2.7, 'iris_143': 3.2, 'iris_144': 3.3, 'iris_145': 3.0, 'iris_146': 2.5, 'iris_147': 3.0, 'iris_148': 3.4, 'iris_149': 3.0}, 'petal_length': {'iris_0': 1.4, 'iris_1': 1.4, 'iris_2': 1.3, 'iris_3': 1.5, 'iris_4': 1.4, 'iris_5': 1.7, 'iris_6': 1.4, 'iris_7': 1.5, 'iris_8': 1.4, 'iris_9': 1.5, 'iris_10': 1.5, 'iris_11': 1.6, 'iris_12': 1.4, 'iris_13': 1.1, 'iris_14': 1.2, 'iris_15': 1.5, 'iris_16': 1.3, 'iris_17': 1.4, 'iris_18': 1.7, 'iris_19': 1.5, 'iris_20': 1.7, 'iris_21': 1.5, 'iris_22': 1.0, 'iris_23': 1.7, 'iris_24': 1.9, 'iris_25': 1.6, 'iris_26': 1.6, 'iris_27': 1.5, 'iris_28': 1.4, 'iris_29': 1.6, 'iris_30': 1.6, 'iris_31': 1.5, 'iris_32': 1.5, 'iris_33': 1.4, 'iris_34': 1.5, 'iris_35': 1.2, 'iris_36': 1.3, 'iris_37': 1.4, 'iris_38': 1.3, 'iris_39': 1.5, 'iris_40': 1.3, 'iris_41': 1.3, 'iris_42': 1.3, 'iris_43': 1.6, 'iris_44': 1.9, 'iris_45': 1.4, 'iris_46': 1.6, 'iris_47': 1.4, 'iris_48': 1.5, 'iris_49': 1.4, 'iris_50': 4.7, 'iris_51': 4.5, 'iris_52': 4.9, 'iris_53': 4.0, 'iris_54': 4.6, 'iris_55': 4.5, 'iris_56': 4.7, 'iris_57': 3.3, 'iris_58': 4.6, 'iris_59': 3.9, 'iris_60': 3.5, 'iris_61': 4.2, 'iris_62': 4.0, 'iris_63': 4.7, 'iris_64': 3.6, 'iris_65': 4.4, 'iris_66': 4.5, 'iris_67': 4.1, 'iris_68': 4.5, 'iris_69': 3.9, 'iris_70': 4.8, 'iris_71': 4.0, 'iris_72': 4.9, 'iris_73': 4.7, 'iris_74': 4.3, 'iris_75': 4.4, 'iris_76': 4.8, 'iris_77': 5.0, 'iris_78': 4.5, 'iris_79': 3.5, 'iris_80': 3.8, 'iris_81': 3.7, 'iris_82': 3.9, 'iris_83': 5.1, 'iris_84': 4.5, 'iris_85': 4.5, 'iris_86': 4.7, 'iris_87': 4.4, 'iris_88': 4.1, 'iris_89': 4.0, 'iris_90': 4.4, 'iris_91': 4.6, 'iris_92': 4.0, 'iris_93': 3.3, 'iris_94': 4.2, 'iris_95': 4.2, 'iris_96': 4.2, 'iris_97': 4.3, 'iris_98': 3.0, 'iris_99': 4.1, 'iris_100': 6.0, 'iris_101': 5.1, 'iris_102': 5.9, 'iris_103': 5.6, 'iris_104': 5.8, 'iris_105': 6.6, 'iris_106': 4.5, 'iris_107': 6.3, 'iris_108': 5.8, 'iris_109': 6.1, 'iris_110': 5.1, 'iris_111': 5.3, 'iris_112': 5.5, 'iris_113': 5.0, 'iris_114': 5.1, 'iris_115': 5.3, 'iris_116': 5.5, 'iris_117': 6.7, 'iris_118': 6.9, 'iris_119': 5.0, 'iris_120': 5.7, 'iris_121': 4.9, 'iris_122': 6.7, 'iris_123': 4.9, 'iris_124': 5.7, 'iris_125': 6.0, 'iris_126': 4.8, 'iris_127': 4.9, 'iris_128': 5.6, 'iris_129': 5.8, 'iris_130': 6.1, 'iris_131': 6.4, 'iris_132': 5.6, 'iris_133': 5.1, 'iris_134': 5.6, 'iris_135': 6.1, 'iris_136': 5.6, 'iris_137': 5.5, 'iris_138': 4.8, 'iris_139': 5.4, 'iris_140': 5.6, 'iris_141': 5.1, 'iris_142': 5.1, 'iris_143': 5.9, 'iris_144': 5.7, 'iris_145': 5.2, 'iris_146': 5.0, 'iris_147': 5.2, 'iris_148': 5.4, 'iris_149': 5.1}, 'petal_width': {'iris_0': 0.2, 'iris_1': 0.2, 'iris_2': 0.2, 'iris_3': 0.2, 'iris_4': 0.2, 'iris_5': 0.4, 'iris_6': 0.3, 'iris_7': 0.2, 'iris_8': 0.2, 'iris_9': 0.1, 'iris_10': 0.2, 'iris_11': 0.2, 'iris_12': 0.1, 'iris_13': 0.1, 'iris_14': 0.2, 'iris_15': 0.4, 'iris_16': 0.4, 'iris_17': 0.3, 'iris_18': 0.3, 'iris_19': 0.3, 'iris_20': 0.2, 'iris_21': 0.4, 'iris_22': 0.2, 'iris_23': 0.5, 'iris_24': 0.2, 'iris_25': 0.2, 'iris_26': 0.4, 'iris_27': 0.2, 'iris_28': 0.2, 'iris_29': 0.2, 'iris_30': 0.2, 'iris_31': 0.4, 'iris_32': 0.1, 'iris_33': 0.2, 'iris_34': 0.2, 'iris_35': 0.2, 'iris_36': 0.2, 'iris_37': 0.1, 'iris_38': 0.2, 'iris_39': 0.2, 'iris_40': 0.3, 'iris_41': 0.3, 'iris_42': 0.2, 'iris_43': 0.6, 'iris_44': 0.4, 'iris_45': 0.3, 'iris_46': 0.2, 'iris_47': 0.2, 'iris_48': 0.2, 'iris_49': 0.2, 'iris_50': 1.4, 'iris_51': 1.5, 'iris_52': 1.5, 'iris_53': 1.3, 'iris_54': 1.5, 'iris_55': 1.3, 'iris_56': 1.6, 'iris_57': 1.0, 'iris_58': 1.3, 'iris_59': 1.4, 'iris_60': 1.0, 'iris_61': 1.5, 'iris_62': 1.0, 'iris_63': 1.4, 'iris_64': 1.3, 'iris_65': 1.4, 'iris_66': 1.5, 'iris_67': 1.0, 'iris_68': 1.5, 'iris_69': 1.1, 'iris_70': 1.8, 'iris_71': 1.3, 'iris_72': 1.5, 'iris_73': 1.2, 'iris_74': 1.3, 'iris_75': 1.4, 'iris_76': 1.4, 'iris_77': 1.7, 'iris_78': 1.5, 'iris_79': 1.0, 'iris_80': 1.1, 'iris_81': 1.0, 'iris_82': 1.2, 'iris_83': 1.6, 'iris_84': 1.5, 'iris_85': 1.6, 'iris_86': 1.5, 'iris_87': 1.3, 'iris_88': 1.3, 'iris_89': 1.3, 'iris_90': 1.2, 'iris_91': 1.4, 'iris_92': 1.2, 'iris_93': 1.0, 'iris_94': 1.3, 'iris_95': 1.2, 'iris_96': 1.3, 'iris_97': 1.3, 'iris_98': 1.1, 'iris_99': 1.3, 'iris_100': 2.5, 'iris_101': 1.9, 'iris_102': 2.1, 'iris_103': 1.8, 'iris_104': 2.2, 'iris_105': 2.1, 'iris_106': 1.7, 'iris_107': 1.8, 'iris_108': 1.8, 'iris_109': 2.5, 'iris_110': 2.0, 'iris_111': 1.9, 'iris_112': 2.1, 'iris_113': 2.0, 'iris_114': 2.4, 'iris_115': 2.3, 'iris_116': 1.8, 'iris_117': 2.2, 'iris_118': 2.3, 'iris_119': 1.5, 'iris_120': 2.3, 'iris_121': 2.0, 'iris_122': 2.0, 'iris_123': 1.8, 'iris_124': 2.1, 'iris_125': 1.8, 'iris_126': 1.8, 'iris_127': 1.8, 'iris_128': 2.1, 'iris_129': 1.6, 'iris_130': 1.9, 'iris_131': 2.0, 'iris_132': 2.2, 'iris_133': 1.5, 'iris_134': 1.4, 'iris_135': 2.3, 'iris_136': 2.4, 'iris_137': 1.8, 'iris_138': 1.8, 'iris_139': 2.1, 'iris_140': 2.4, 'iris_141': 2.3, 'iris_142': 1.9, 'iris_143': 2.3, 'iris_144': 2.5, 'iris_145': 2.3, 'iris_146': 1.9, 'iris_147': 2.0, 'iris_148': 2.3, 'iris_149': 1.8}})
# Dissimilarity
df_dism = 1 - X_iris.T.corr().abs()
# Convert to R dataframe
rkernel = pandas_to_rpy2(df_dism.values)
# Should I use R() or R[] to convert to dissimilarity object
rdism = R("as.dist")(rkernel)
# rdism = R["as.dist"](rkernel)
# rdism = r_stats.as_dist(rkernel)
# Why does it return a numpy array
print(type(rdism))
# <class 'numpy.ndarray'>
# Load in fastcluster package
fastcluster.hclust(rdism)
# Regular HCLUST doesn't even work
# R.hclust(rdism)
# R[write to console]: Error in (function (d, method = "complete", members = NULL) :
# 'N' must be a single integer.
# ---------------------------------------------------------------------------
# RRuntimeError Traceback (most recent call last)
# <ipython-input-93-487d69feeea3> in <module>
# 21 # rdism = r_stats.as_dist(rkernel)
# 22
# ---> 23 R.hclust(rdism)
# 24
# 25
# ~/anaconda3/envs/soothsayer2_env/lib/python3.6/site-packages/rpy2/robjects/functions.py in __call__(self, *args, **kwargs)
# 196 kwargs[r_k] = v
# 197 return (super(SignatureTranslatedFunction, self)
# --> 198 .__call__(*args, **kwargs))
# 199
# 200
# ~/anaconda3/envs/soothsayer2_env/lib/python3.6/site-packages/rpy2/robjects/functions.py in __call__(self, *args, **kwargs)
# 123 else:
# 124 new_kwargs[k] = conversion.py2rpy(v)
# --> 125 res = super(Function, self).__call__(*new_args, **new_kwargs)
# 126 res = conversion.rpy2py(res)
# 127 return res
# ~/anaconda3/envs/soothsayer2_env/lib/python3.6/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)
# ~/anaconda3/envs/soothsayer2_env/lib/python3.6/site-packages/rpy2/rinterface.py in __call__(self, *args, **kwargs)
# 619 error_occured))
# 620 if error_occured[0]:
# --> 621 raise embedded.RRuntimeError(_rinterface._geterrmessage())
# 622 return res
# 623
# RRuntimeError: Error in (function (d, method = "complete", members = NULL) :
# 'N' must be a single integer.
[您可能想使用数据框而不是矩阵（正如您的注释所表明的那样，所以您应该使用df_dism而不是df_dism.values（这将提供一个numpy数组）。
此外，要使用熊猫转换，您需要调整转换功能以与rpy2 3.x一起使用：
from rpy2.robjects.conversion import localconverter
from rpy2.robjects import pandas2ri
def pandas_to_rpy2(df):
with localconverter(ro.default_converter + pandas2ri.converter):
return ro.conversion.py2rpy(df)
def rpy2_to_pandas(r_df):
with localconverter(ro.default_converter + pandas2ri.converter):
return ro.conversion.rpy2py(r_df)
rkernel = pandas_to_rpy2(df_dism)
然后type(rdism)返回<class 'rpy2.robjects.vectors.FloatVector'>，并且两者：fastcluster.hclust(rdism)和R.hclust(rdism)正常工作。
经过测试：
关于您的第一个问题，首选使用R["as.dist"]方法来获取对象（并且在这种情况下，由于函数是对象，所以可以正常工作），而首选R("as.dist")来评估R代码（as.dist的结果为a函数对象，因此最终结果是相同的）。看看文档的introduction section，它们都与pi对象一起使用。
因为不需要评估，所以R["as.dist"]会更快：
%timeit R("as.dist")
1.75 ms ± 238 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
%timeit R["as.dist"]
473 µs ± 36.9 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)
为了突出实现R["as.dist"]的差异，将执行：
def __getitem__(self, item):
res = _globalenv.find(item)
res = conversion.rpy2py(res)
if hasattr(res, '__rname__'):
res.__rname__ = item
return res
在R("as.dist")期间：
def __call__(self, string):
p = rinterface.parse(string)
res = self.eval(p)
return conversion.rpy2py(res)
总之，在这种情况下，我将使用R [“ as.dist”]，因为它速度稍快，并且更好地反映了意图。