Last active
October 16, 2015 20:52
-
-
Save jbn/1f8d0d6a14d6fe40b94e to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import numpy as np | |
import pandas as pd | |
import rpy2 | |
from rpy2 import robjects | |
from rpy2.robjects.packages import importr | |
AMELIA = importr("Amelia") | |
NAN_TO_NA_MAP = {np.dtype('float'): robjects.NA_Real, | |
np.dtype('int'): robjects.NA_Integer, | |
np.dtype('O'): robjects.NA_Character} | |
DTYPE_TO_F = {np.dtype('float'): robjects.FloatVector, | |
np.dtype('int'): robjects.IntVector, | |
np.dtype('O'): robjects.StrVector} | |
def can_be_int(xs): | |
for x in xs: | |
try: | |
if not np.isnan(x): | |
assert int(x) == x | |
except: | |
return False | |
return True | |
# The conversion from a pandas DataFrame to a R data.frame doesn't work well | |
# for Amelia imputation. Amelia imputes given a NA, not a NAN. In R, the | |
# former indicates a missing value, the later, a bad operation. Unfortunately, | |
# Pandas doesn't distinguish between the two. So, this function builds an R | |
# data.frame from a Pandas' one, assuming you want NA not NAN. | |
def df_py_nan_to_r_na(df): | |
d = {} | |
for col in df.columns: | |
xs = df[col] | |
# There are no int-based numpy arrays. Everything must be a | |
# float, if it is numeric. R has integer-based arrays. Where | |
# possible, make the array integer based. | |
dtype = xs.dtype | |
if dtype == np.dtype('float') and can_be_int(xs): | |
dtype = np.dtype('int') | |
R_NA = NAN_TO_NA_MAP[dtype] | |
xs = [R_NA if c else x for c, x in zip(xs.isnull(), xs)] | |
d[col] = DTYPE_TO_F[dtype](xs) | |
return robjects.DataFrame(d) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment