#21 - rename files and functions to make them more inline with standa…

impyute/__init__.py

@@ -13,17 +13,17 @@
 
 ### Top Level Modules
 
-__all__ = ["datasets", "utils", "deletions", "filters"]
+__all__ = ["dataset", "util", "deletion", "filter"]
 
 ### Cross Sectional Imputations
 
-from impyute.imputations.cs import mean_imputation as mean
-from impyute.imputations.cs import median_imputation as median
-from impyute.imputations.cs import mode_imputation as mode
-from impyute.imputations.cs import em
-from impyute.imputations.cs import fast_knn
-from impyute.imputations.cs import mice
-from impyute.imputations.cs import random_imputation as random
+from impyute.imputation.cs import mean
+from impyute.imputation.cs import median
+from impyute.imputation.cs import mode
+from impyute.imputation.cs import em
+from impyute.imputation.cs import fast_knn
+from impyute.imputation.cs import mice
+from impyute.imputation.cs import random
 
 __all__.extend([
     "mean",
@@ -37,16 +37,16 @@
 
 ### Time Series Imputations
 
-from impyute.imputations.ts import locf
-from impyute.imputations.ts import arima
+from impyute.imputation.ts import locf
+from impyute.imputation.ts import arima
 
 __all__.extend([
     "locf",
     "arima"
 ])
 
 ### Deletions
-from impyute.deletions import complete_case
+from impyute.deletion import complete_case
 
 __all__.extend([
     "complete_case"

impyute/datasets/__init__.py → impyute/dataset/__init__.py

@@ -1,9 +1,9 @@
 """
 Real-world/mock datasets and missingness corruptors to experiment with.
 """
-from .base import random_uniform
-from .base import random_normal
+from .base import randu
+from .base import randn
 from .base import test_data
 from .base import mnist
 
-__all__ = ["random_uniform", "random_normal", "test_data", "mnist"]
+__all__ = ["randu", "randn", "test_data", "mnist"]

impyute/datasets/base.py → impyute/dataset/base.py

@@ -1,13 +1,13 @@
-""" impyute.datasets.base
+""" impyute.dataset.base
 
 Load/generate data
 
 """
 import numpy as np
-from impyute.datasets.corrupt import Corruptor
+from impyute.dataset.corrupt import Corruptor
 
 
-def random_uniform(bound=(0, 10), shape=(5, 5), missingness="mcar",
+def randu(bound=(0, 10), shape=(5, 5), missingness="mcar",
                    thr=0.2, dtype="int"):
     """ Return randomly generated dataset of numbers with uniformly
     distributed values between bound[0] and bound[1]
@@ -40,7 +40,7 @@ def random_uniform(bound=(0, 10), shape=(5, 5), missingness="mcar",
     return raw_data
 
 
-def random_normal(theta=(0, 1), shape=(5, 5), missingness="mcar", thr=0.2,
+def randn(theta=(0, 1), shape=(5, 5), missingness="mcar", thr=0.2,
                   dtype="float"):
     """ Return randomly generated dataset of numbers with normally
     distributed values with given and sigma.

impyute/datasets/corrupt.py → impyute/dataset/corrupt.py

@@ -1,4 +1,4 @@
-""" impyute.datasets.corrupt """
+""" impyute.dataset.corrupt """
 import numpy as np
 
 

impyute/deletions/complete_case.py → impyute/deletion/complete_case.py

@@ -1,4 +1,4 @@
-""" impyute.deletions.complete_case """
+""" impyute.deletion.complete_case """
 import numpy as np
 
 def complete_case(data):

impyute/imputation/cs/__init__.py

@@ -0,0 +1,14 @@
+"""
+Imputations for cross-sectional data.
+"""
+
+from .random import random
+from .central_tendency import mean
+from .central_tendency import mode
+from .central_tendency import median
+from .mice import mice
+from .em import em
+from .fast_knn import fast_knn
+
+__all__ = ["random", "mean", "mode",
+           "median", "mice", "em", "fast_knn"]

impyute/imputations/cs/averaging_imputations.py → impyute/imputation/cs/central_tendency.py

@@ -1,14 +1,14 @@
-""" impyute.imputations.cs.averaging_imputations """
+""" impyute.imputation.cs.central_tendency """
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import checks
-from impyute.utils import preprocess
+from impyute.util import find_null
+from impyute.util import checks
+from impyute.util import preprocess
 # pylint:disable=unused-argument
 # pylint:disable=invalid-name
 
 @preprocess
 @checks
-def mean_imputation(data, **kwargs):
+def mean(data, **kwargs):
     """ Substitute missing values with the mean of that column.
 
     Parameters
@@ -31,7 +31,7 @@ def mean_imputation(data, **kwargs):
 
 @preprocess
 @checks
-def median_imputation(data, **kwargs):
+def median(data, **kwargs):
     """ Substitute missing values with the median of that column(middle).
 
     Parameters
@@ -58,7 +58,7 @@ def median_imputation(data, **kwargs):
 
 @preprocess
 @checks
-def mode_imputation(data, **kwargs):
+def mode(data, **kwargs):
     """ Substitute missing values with the mode of that column(most frequent).
 
     In the case that there is a tie (there are multiple, most frequent values)

impyute/imputations/cs/em.py → impyute/imputation/cs/em.py

@@ -1,9 +1,8 @@
-""" impyute.imputations.cs.em"""
-import random
+""" impyute.imputation.cs.em"""
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import preprocess
-from impyute.utils import checks
+from impyute.util import find_null
+from impyute.util import preprocess
+from impyute.util import checks
 # pylint:disable=invalid-name
 # pylint:disable=unused-argument
 
@@ -36,14 +35,14 @@ def em(data, loops=50, **kwargs):
         col = data[:, int(y_i)]
         mu = col[~np.isnan(col)].mean()
         std = col[~np.isnan(col)].std()
-        col[x_i] = random.gauss(mu, std)
+        col[x_i] = np.random.normal(loc=mu, scale=std)
         previous, i = 1, 1
         for i in range(loops):
             # Expectation
             mu = col[~np.isnan(col)].mean()
             std = col[~np.isnan(col)].std()
             # Maximization
-            col[x_i] = random.gauss(mu, std)
+            col[x_i] = np.random.normal(loc=mu, scale=std)
             # Break out of loop if likelihood doesn't change at least 10%
             # and has run at least 5 times
             delta = (col[x_i]-previous)/previous

impyute/imputations/cs/fast_knn.py → impyute/imputation/cs/fast_knn.py

@@ -1,9 +1,9 @@
-""" impyute.imputations.cs.knn"""
+""" impyute.imputation.cs.knn """
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import checks
-from impyute.utils import preprocess
-from impyute.imputations.cs import mean_imputation
+from impyute.util import find_null
+from impyute.util import checks
+from impyute.util import preprocess
+from impyute.imputation.cs import mean
 from scipy.spatial import KDTree
 # pylint: disable=invalid-name
 # pylint:disable=unused-argument
@@ -32,7 +32,7 @@ def fast_knn(data, k=3, **kwargs):
 
     """
     null_xy = find_null(data)
-    data_c = mean_imputation(data)
+    data_c = mean(data)
     kdtree = KDTree(data_c)
 
     for x_i, y_i in null_xy:

impyute/imputations/cs/mice.py → impyute/imputation/cs/mice.py

@@ -1,9 +1,9 @@
-"""imputations.cs.mice"""
+""" impyute.imputation.cs.mice """
 import numpy as np
 from sklearn.linear_model import LinearRegression
-from impyute.utils import find_null
-from impyute.utils import checks
-from impyute.utils import preprocess
+from impyute.util import find_null
+from impyute.util import checks
+from impyute.util import preprocess
 # pylint: disable=too-many-locals
 # pylint:disable=invalid-name
 # pylint:disable=unused-argument

impyute/imputations/cs/random_imputation.py → impyute/imputation/cs/random.py

@@ -1,14 +1,14 @@
-""" impyute.imputations.cs.random_imputation"""
+""" impyute.imputation.cs.random """
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import preprocess
-from impyute.utils import checks
+from impyute.util import find_null
+from impyute.util import preprocess
+from impyute.util import checks
 # pylint:disable=invalid-name
 # pylint:disable=unused-argument
 
 @preprocess
 @checks
-def random_imputation(data, **kwargs):
+def random(data, **kwargs):
     """ Fill missing values in with a randomly selected value from the same
     column.
 

impyute/imputations/ts/arima.py → impyute/imputation/ts/arima.py

@@ -1,7 +1,6 @@
-"""Autoregressive Integrated Moving Average Imputation"""
-import numpy as np
-from impyute.utils import find_null
-from impyute.utils import checks
+""" impyute.imputation.ts.arima """
+from impyute.util import find_null
+from impyute.util import checks
 # pylint: disable=invalid-name
 
 @checks

impyute/imputations/ts/locf.py → impyute/imputation/ts/locf.py

@@ -1,7 +1,7 @@
-""" impyute.imputations.ts.locf """
+""" impyute.imputation.ts.locf """
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import checks
+from impyute.util import find_null
+from impyute.util import checks
 
 
 @checks

impyute/utils/__init__.py → impyute/util/__init__.py

@@ -3,7 +3,6 @@
 """
 
 from .find_null import find_null
-from .loggers import print_io
 from .describe import describe
 # from .mcar_test import mcar_test
 from .count_missing import count_missing
@@ -12,5 +11,5 @@
 from .compare import compare
 from .preprocess import preprocess
 
-__all__ = ["find_null", "print_io", "describe", "count_missing",
+__all__ = ["find_null", "describe", "count_missing",
            "checks", "compare", "BadInputError", "preprocess"]

impyute/utils/checks.py → impyute/util/checks.py

@@ -1,8 +1,8 @@
-""" impyute.utils.check """
+""" impyute.util.check """
 from functools import wraps
 import numpy as np
-from impyute.utils import find_null
-from impyute.utils import BadInputError
+from impyute.util import find_null
+from impyute.util import BadInputError
 # pylint:disable=invalid-name
 
 def checks(fn):

impyute/utils/compare.py → impyute/util/compare.py

@@ -1,4 +1,4 @@
-"""impyute.utils.compare.py"""
+"""impyute.util.compare.py"""
 import importlib
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score

impyute/utils/count_missing.py → impyute/util/count_missing.py

@@ -1,6 +1,6 @@
-""" impyute.utils.count_missing.py """
+""" impyute.util.count_missing.py """
 import numpy as np
-from impyute.utils import find_null
+from impyute.util import find_null
 
 
 def count_missing(data):

impyute/utils/describe.py → impyute/util/describe.py

@@ -1,5 +1,5 @@
-""" impyute.utils.describe """
-from impyute.utils import find_null
+""" impyute.util.describe """
+from impyute.util import find_null
 
 
 def describe(data): # verbose=True):

impyute/utils/errors.py → impyute/util/errors.py

@@ -1,4 +1,4 @@
-""" impyute.utils.errors """
+""" impyute.util.errors """
 class BadInputError(Exception):
     def __init__(self, value):
         self.value = value

impyute/utils/find_null.py → impyute/util/find_null.py

@@ -1,4 +1,4 @@
-""" impyute.utils.find_null """
+""" impyute.util.find_null """
 import numpy as np
 
 

impyute/utils/preprocess.py → impyute/util/preprocess.py

@@ -1,4 +1,4 @@
-""" impyute.utils.preprocess """
+""" impyute.util.preprocess """
 from functools import wraps
 # pylint:disable=invalid-name
 

test/datasets/test_mnist.py → test/dataset/test_mnist.py

@@ -1,8 +1,8 @@
 """test_mnist.py"""
 import unittest
 import numpy as np
-from impyute.datasets import mnist
-from impyute.utils import find_null
+from impyute.dataset import mnist
+from impyute.util import find_null
 
 
 @unittest.skip("takes a long time, adds 30 sec for each test")

test/deletions/test_complete_case.py → test/deletion/test_complete_case.py

@@ -1,9 +1,9 @@
 """test_complete_case.py"""
 import unittest
 import numpy as np
-from impyute.datasets import test_data
-from impyute.deletions import complete_case
-from impyute.utils import checks
+from impyute.dataset import test_data
+from impyute.deletion import complete_case
+from impyute.util import checks
 
 @checks
 class TestCC(unittest.TestCase):