Clumper

This object adds methods to a list of dictionaries that make it nicer to explore.

Usage:

from clumper import Clumper

list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

c = Clumper(list_dicts)

agg(self, **kwargs)

Show source code in clumper/clump.py
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
    @dict_collection_only
    @grouped
    def agg(self, **kwargs):
        """
        Does an aggregation on a collection of dictionaries. If there are no groups active
        then this method will create a single dictionary containing a summary. If there are
        groups active then the dataset will first split up, then apply the summaries after
        which everything is combined again into a single collection.

        When defining a summary to apply you'll need to pass three things:

        1. the name of the new key
        2. the key you'd like to summarise (first item in the tuple)
        3. the summary you'd like to calculate on that key (second item in the tuple)

        It can also accept a string and it will try to fetch an appropriate function
        for you. If you pass a string it must be either: `mean`, `count`, `unique`,
        `n_unique`, `sum`, `min`, `max`, `median`, `values`, `var`, `std`, `first` or `last`.

        ![](../img/split-apply-combine.png)

        Warning:
            This method is aware of groups. There may be different results if a group is active.

        Arguments:
            kwargs: keyword arguments that represent the aggregation that is about to happen, see usage below.

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [
            {'a': 1, 'b': 2},
            {'a': 2, 'b': 3},
            {'a': 3}
        ]

        (Clumper(list_dicts)
          .agg(mean_a=('a', 'mean'),
               min_b=('b', 'min'),
               max_b=('b', 'max'))
          .collect())

        another_list_dicts = [
            {'a': 1, 'c': 'a'},
            {'a': 2, 'c': 'b'},
            {'a': 3, 'c': 'a'}
        ]

        (Clumper(another_list_dicts)
          .group_by('c')
          .agg(mean_a=('a', 'mean'),
               uniq_a=('a', 'unique'))
          .collect())
        ```

        Advanced Usage:

        You can also supply this verb your own functions if you'd like.

        ```python
        from clumper import Clumper

        data = [
            {"a": 6, "grp": "a"},
            {"a": 2, "grp": "b"},
            {"a": 7, "grp": "a"},
            {"a": 9, "grp": "b"},
            {"a": 5, "grp": "a"}
        ]

        tfm_clump = (Clumper(data)
                      .group_by("grp")
                      .transform(s=("a", sum),
                                 u=("a", lambda x: len(set(x)))

        expected = [
            {'a': 6, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 7, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 5, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 2, 'grp': 'b', 's': 11, 'u': [9, 2]},
            {'a': 9, 'grp': 'b', 's': 11, 'u': [9, 2]}
        ]

        assert tfm_clump.equals(expected)
        ```
        """
        res = {
            name: self.summarise_col(func_str, col)
            for name, (col, func_str) in kwargs.items()
        }
        return Clumper([res], groups=self.groups)

Does an aggregation on a collection of dictionaries. If there are no groups active then this method will create a single dictionary containing a summary. If there are groups active then the dataset will first split up, then apply the summaries after which everything is combined again into a single collection.

When defining a summary to apply you'll need to pass three things:

  1. the name of the new key
  2. the key you'd like to summarise (first item in the tuple)
  3. the summary you'd like to calculate on that key (second item in the tuple)

It can also accept a string and it will try to fetch an appropriate function for you. If you pass a string it must be either: mean, count, unique, n_unique, sum, min, max, median, values, var, std, first or last.

Warning

This method is aware of groups. There may be different results if a group is active.

Parameters

Name Type Description Default
**kwargs keyword arguments that represent the aggregation that is about to happen, see usage below. {}

Usage:

from clumper import Clumper

list_dicts = [
    {'a': 1, 'b': 2},
    {'a': 2, 'b': 3},
    {'a': 3}
]

(Clumper(list_dicts)
  .agg(mean_a=('a', 'mean'),
       min_b=('b', 'min'),
       max_b=('b', 'max'))
  .collect())

another_list_dicts = [
    {'a': 1, 'c': 'a'},
    {'a': 2, 'c': 'b'},
    {'a': 3, 'c': 'a'}
]

(Clumper(another_list_dicts)
  .group_by('c')
  .agg(mean_a=('a', 'mean'),
       uniq_a=('a', 'unique'))
  .collect())

Advanced Usage:

You can also supply this verb your own functions if you'd like.

from clumper import Clumper

data = [
    {"a": 6, "grp": "a"},
    {"a": 2, "grp": "b"},
    {"a": 7, "grp": "a"},
    {"a": 9, "grp": "b"},
    {"a": 5, "grp": "a"}
]

tfm_clump = (Clumper(data)
              .group_by("grp")
              .transform(s=("a", sum),
                         u=("a", lambda x: len(set(x)))

expected = [
    {'a': 6, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 7, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 5, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 2, 'grp': 'b', 's': 11, 'u': [9, 2]},
    {'a': 9, 'grp': 'b', 's': 11, 'u': [9, 2]}
]

assert tfm_clump.equals(expected)

collect(self)

Show source code in clumper/clump.py
1234
1235
1236
1237
1238
1239
1240
    def collect(self):
        """
        Returns a list instead of a `Clumper` object.

        ![](../img/collect.png)
        """
        return self.blob

Returns a list instead of a Clumper object.

concat(self, *other)

Show source code in clumper/clump.py
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
    def concat(self, *other):
        """
        Concatenate two or more `Clumper` objects together.

        ![](../img/concat.png)

        ```python
        from clumper import Clumper

        c1 = Clumper([{"a": 1}])
        c2 = Clumper([{"a": 2}])
        c3 = Clumper([{"a": 3}])

        assert len(c1.concat(c2)) == 2
        assert len(c1.concat(c2, c3)) == 3
        assert len(c1.concat(c2).concat(c3)) == 3
        ```
        """

        data = reduce(lambda a, b: a + b, [o.blob for o in other])
        return self._create_new(self.blob + data)

Concatenate two or more Clumper objects together.

from clumper import Clumper

c1 = Clumper([{"a": 1}])
c2 = Clumper([{"a": 2}])
c3 = Clumper([{"a": 3}])

assert len(c1.concat(c2)) == 2
assert len(c1.concat(c2, c3)) == 3
assert len(c1.concat(c2).concat(c3)) == 3

copy(self)

Show source code in clumper/clump.py
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
    def copy(self):
        """
        Makes a copy of the collection.

        ![](../img/copy.png)

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': i} for i in range(100)]

        c1 = Clumper(list_dicts)
        c2 = c1.copy()
        assert id(c1) != id(c2)
        ```
        """
        return self._create_new([d for d in self.blob])

Makes a copy of the collection.

Usage:

from clumper import Clumper

list_dicts = [{'a': i} for i in range(100)]

c1 = Clumper(list_dicts)
c2 = c1.copy()
assert id(c1) != id(c2)

count(self, col)

Show source code in clumper/clump.py
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
    @dict_collection_only
    @return_value_if_empty(value=0)
    def count(self, col):
        """
        Counts how often a key appears in the collection.

        ![](../img/count.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert Clumper(list_of_dicts).count("a") == 4
        assert Clumper(list_of_dicts).count("b") == 3
        ```
        """
        return self.summarise_col("count", col)

Counts how often a key appears in the collection.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert Clumper(list_of_dicts).count("a") == 4
assert Clumper(list_of_dicts).count("b") == 3

drop(self, *keys)

Show source code in clumper/clump.py
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
    @dict_collection_only
    def drop(self, *keys):
        """
        Removes a subset of keys from each item in the collection.

        ![](../img/drop.png)

        Arguments:
            keys: the keys to remove

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [
            {'a': 1, 'b': 2},
            {'a': 2, 'b': 3, 'c':4},
            {'a': 1, 'b': 6}]

        clump = Clumper(list_dicts).drop('c')
        assert all(["c" not in d.keys() for d in clump])
        ```
        """
        return self._create_new(
            [{k: v for k, v in d.items() if k not in keys} for d in self.blob]
        )

Removes a subset of keys from each item in the collection.

Parameters

Name Type Description Default
*keys the keys to remove ()

Usage:

from clumper import Clumper

list_dicts = [
    {'a': 1, 'b': 2},
    {'a': 2, 'b': 3, 'c':4},
    {'a': 1, 'b': 6}]

clump = Clumper(list_dicts).drop('c')
assert all(["c" not in d.keys() for d in clump])

drop_duplicates(self)

Show source code in clumper/clump.py
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
    def drop_duplicates(self):
        """
        Iterates over all elements to remove duplicates.

        ![](../img/drop_duplicates.png)

        Usage:

        ```python
        from clumper import Clumper

        data = [{"a": 1}, {"a": 2}, {"a": 2}]
        clump = Clumper(data).drop_duplicates()
        expected = [{"a": 1}, {"a": 2}]
        assert clump.equals(expected)
        ```
        """
        uniques = []
        for d in self:
            if d not in uniques:
                uniques.append(d)
        return self._create_new(uniques)

Iterates over all elements to remove duplicates.

Usage:

from clumper import Clumper

data = [{"a": 1}, {"a": 2}, {"a": 2}]
clump = Clumper(data).drop_duplicates()
expected = [{"a": 1}, {"a": 2}]
assert clump.equals(expected)

equals(self, data)

Show source code in clumper/clump.py
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
    def equals(self, data):
        """
        Compares the collection of items with a list. Returns `True` if they have the same contents.
        Note that we do not care about the order of the elements.

        This method is used internally for testing but it can also be very useful for bug reporting.

        ![](../img/equals.png)

        Arguments:
            data: a list of that to compare against

        Usage:

        ```python
        from clumper import Clumper

        data = [{"a": 1}]
        clump = Clumper(data)
        assert clump.equals(data)
        assert not clump.equals([{"b":1}])
        ```
        """
        for i in self:
            if i not in data:
                return False
        for i in data:
            if i not in self:
                return False
        return True

Compares the collection of items with a list. Returns True if they have the same contents. Note that we do not care about the order of the elements.

This method is used internally for testing but it can also be very useful for bug reporting.

Parameters

Name Type Description Default
data a list of that to compare against required

Usage:

from clumper import Clumper

data = [{"a": 1}]
clump = Clumper(data)
assert clump.equals(data)
assert not clump.equals([{"b":1}])

explode(self, *to_explode, **kwargs)

Show source code in clumper/clump.py
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
    @dict_collection_only
    def explode(self, *to_explode, **kwargs):
        """
        Turns a list in an item into multiple items. The opposite of `.implode()`.

        ![](../img/explode.png)

        Arguments:
            to_explode: keys to explode, will keep the same name
            kwargs: (new name, keys to explode)-pairs

        Usage:

        ```python
        from clumper import Clumper

        data = [{'a': 1, 'items': [1, 2]}]

        clumper = Clumper(data).explode("items")
        expected = [{'a': 1, 'items': 1}, {'a': 1, 'items': 2}]
        assert clumper.equals(expected)

        clumper = Clumper(data).explode(item="items")
        expected = [{'a': 1, 'item': 1}, {'a': 1, 'item': 2}]
        assert clumper.equals(expected)
        ```
        """
        # you can keep the same name by just using *args or overwrite using **kwargs
        kwargs = {**kwargs, **{k: k for k in to_explode}}
        new_name, to_explode = kwargs.keys(), kwargs.values()

        res = []
        for d in self.blob:
            combinations = it.product(*[d[v] for v in to_explode])
            for comb in combinations:
                new_dict = d.copy()
                for k, v in zip(new_name, comb):
                    new_dict[k] = v
                res.append(new_dict)
        return self._create_new(res).drop(*[k for k in to_explode if k not in new_name])

Turns a list in an item into multiple items. The opposite of .implode().

Parameters

Name Type Description Default
*to_explode keys to explode, will keep the same name ()
**kwargs (new name, keys to explode)-pairs {}

Usage:

from clumper import Clumper

data = [{'a': 1, 'items': [1, 2]}]

clumper = Clumper(data).explode("items")
expected = [{'a': 1, 'items': 1}, {'a': 1, 'items': 2}]
assert clumper.equals(expected)

clumper = Clumper(data).explode(item="items")
expected = [{'a': 1, 'item': 1}, {'a': 1, 'item': 2}]
assert clumper.equals(expected)

flatten_keys(self, keyname='key')

Show source code in clumper/clump.py
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
    def flatten_keys(self, keyname="key"):
        """
        Flattens the keys in the data. Useful when `Clumper` is created with a single large dictionary.

        ![](../img/flatten_keys.png)

        Arguments:
            keyname: the name of the new key

        Usage:

        ```python
        from clumper import Clumper

        data = {
          'feature_1': {'propery_1': 1, 'property_2': 2},
          'feature_2': {'propery_1': 3, 'property_2': 4},
          'feature_3': {'propery_1': 5, 'property_2': 6},
        }

        expected = [
            {'propery_1': 1, 'property_2': 2, 'key': 'feature_1'},
            {'propery_1': 3, 'property_2': 4, 'key': 'feature_2'},
            {'propery_1': 5, 'property_2': 6, 'key': 'feature_3'}
        ]

        assert Clumper(data).flatten_keys().collect() == expected
        ```
        """
        return self._create_new([{**v, keyname: k} for k, v in self.blob.items()])

Flattens the keys in the data. Useful when Clumper is created with a single large dictionary.

Parameters

Name Type Description Default
keyname the name of the new key 'key'

Usage:

from clumper import Clumper

data = {
  'feature_1': {'propery_1': 1, 'property_2': 2},
  'feature_2': {'propery_1': 3, 'property_2': 4},
  'feature_3': {'propery_1': 5, 'property_2': 6},
}

expected = [
    {'propery_1': 1, 'property_2': 2, 'key': 'feature_1'},
    {'propery_1': 3, 'property_2': 4, 'key': 'feature_2'},
    {'propery_1': 5, 'property_2': 6, 'key': 'feature_3'}
]

assert Clumper(data).flatten_keys().collect() == expected

group_by(self, *cols)

Show source code in clumper/clump.py
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
    def group_by(self, *cols):
        """
        Sets a group on this clumper object or overrides a previous setting.
        A group will affect how some verbs behave. You can undo this behavior
        with `.ungroup()`.

        ![](../img/groupby.png)

        ```python
        from clumper import Clumper

        clump = Clumper([{"a": 1}]).group_by("a")
        assert clump.groups == ("a", )
        ```
        """
        self.groups = cols
        return self

Sets a group on this clumper object or overrides a previous setting. A group will affect how some verbs behave. You can undo this behavior with .ungroup().

from clumper import Clumper

clump = Clumper([{"a": 1}]).group_by("a")
assert clump.groups == ("a", )

head(self, n=5)

Show source code in clumper/clump.py
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
    def head(self, n=5):
        """
        Selects the top `n` items from the collection.

        ![](../img/head.png)

        Arguments:
            n: the number of items to grab

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

        result = Clumper(list_dicts).head(2)
        expected = [{'a': 1}, {'a': 2}]

        assert result.equals(expected)
        ```
        """
        if not isinstance(n, int):
            raise ValueError(f"`n` must be a positive integer, got {n}")
        if n < 0:
            raise ValueError(f"`n` must be a positive integer, got {n}")
        n = min(n, len(self))
        return self._create_new([self.blob[i] for i in range(n)])

Selects the top n items from the collection.

Parameters

Name Type Description Default
n the number of items to grab 5

Usage:

from clumper import Clumper

list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

result = Clumper(list_dicts).head(2)
expected = [{'a': 1}, {'a': 2}]

assert result.equals(expected)

inner_join(self, other, mapping, lsuffix='', rsuffix='_joined')

Show source code in clumper/clump.py
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
    @dict_collection_only
    def inner_join(self, other, mapping, lsuffix="", rsuffix="_joined"):
        """
        Performs an inner join on two collections.

        ![](../img/inner_join.png)

        Arguments:
            other: another collection to join with
            mapping: a dictionary of **left-keys**:**right-keys** that explain how to join
            lsuffix: a suffix to add to the left keys in case of an overlap
            rsuffix: a suffix to add to the right keys in case of an overlap

        Usage:

        ```python
        from clumper import Clumper

        left = Clumper([
            {"a": 1, "b":4},
            {"a": 2, "b":6},
            {"a": 3, "b":8},
        ])

        right = Clumper([
            {"c": 9, "b":4},
            {"c": 8, "b":5},
            {"c": 7, "b":6},
        ])

        result = left.inner_join(right, mapping={"b": "b"})
        expected = [
            {"a": 1, "b": 4, "c": 9},
            {"a": 2, "b": 6, "c": 7},
        ]

        assert result.equals(expected)
        ```
        """
        result = []
        # This is a naive implementation. Speedup seems possible.
        for d_i in self:
            values_i = [d_i[k] for k in mapping.keys() if k in d_i.keys()]
            for d_j in other:
                values_j = [d_j[k] for k in mapping.values() if k in d_j.keys()]
                if len(mapping) == len(values_i) == len(values_j):
                    if values_i == values_j:
                        result.append(
                            Clumper._merge_dicts(d_i, d_j, mapping, lsuffix, rsuffix)
                        )
        return self._create_new(result)

Performs an inner join on two collections.

Parameters

Name Type Description Default
other another collection to join with required
mapping a dictionary of left-keys:right-keys that explain how to join required
lsuffix a suffix to add to the left keys in case of an overlap ''
rsuffix a suffix to add to the right keys in case of an overlap '_joined'

Usage:

from clumper import Clumper

left = Clumper([
    {"a": 1, "b":4},
    {"a": 2, "b":6},
    {"a": 3, "b":8},
])

right = Clumper([
    {"c": 9, "b":4},
    {"c": 8, "b":5},
    {"c": 7, "b":6},
])

result = left.inner_join(right, mapping={"b": "b"})
expected = [
    {"a": 1, "b": 4, "c": 9},
    {"a": 2, "b": 6, "c": 7},
]

assert result.equals(expected)

keep(self, *funcs)

Show source code in clumper/clump.py
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
    def keep(self, *funcs):
        """
        Allows you to select which items to keep and which items to remove.

        ![](../img/keep.png)

        Arguments:
            funcs: functions that indicate which items to keep

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

        clump = Clumper(list_dicts).keep(lambda d: d['a'] >= 3)
        expected = [{'a': 3}, {'a': 4}]
        assert clump.equals(expected)
        ```
        """
        data = self.blob.copy()
        for func in funcs:
            data = [d for d in data if func(d)]
        return self._create_new(data)

Allows you to select which items to keep and which items to remove.

Parameters

Name Type Description Default
*funcs functions that indicate which items to keep ()

Usage:

from clumper import Clumper

list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

clump = Clumper(list_dicts).keep(lambda d: d['a'] >= 3)
expected = [{'a': 3}, {'a': 4}]
assert clump.equals(expected)

keys(self, overlap=False)

Show source code in clumper/clump.py
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
    @dict_collection_only
    def keys(self, overlap=False):
        """
        Returns all the keys of all the items in the collection.

        ![](../img/keys.png)

        Arguments:
            overlap: if `True` only return the keys that overlap in each set

        Usage:

        ```python
        from clumper import Clumper

        data = [{'a': 1, 'b': 2}, {'a': 2, 'c': 3}]

        assert set(Clumper(data).keys(overlap=True)) == {'a'}
        assert set(Clumper(data).keys(overlap=False)) == {'a', 'b', 'c'}
        ```
        """
        if overlap:
            all_keys = [set(d.keys()) for d in self]
            return list(reduce(lambda a, b: a.intersection(b), all_keys))
        return list({k for d in self for k in d.keys()})

Returns all the keys of all the items in the collection.

Parameters

Name Type Description Default
overlap if True only return the keys that overlap in each set False

Usage:

from clumper import Clumper

data = [{'a': 1, 'b': 2}, {'a': 2, 'c': 3}]

assert set(Clumper(data).keys(overlap=True)) == {'a'}
assert set(Clumper(data).keys(overlap=False)) == {'a', 'b', 'c'}

left_join(self, other, mapping, lsuffix='', rsuffix='_joined')

Show source code in clumper/clump.py
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
    @dict_collection_only
    def left_join(self, other, mapping, lsuffix="", rsuffix="_joined"):
        """
        Performs a left join on two collections.

        Each item from the left set will appear in the final collection. Only
        some items from the right set may appear if a merge is possible. There
        may be multiple copies of the left set if it can be joined multiple times.

        ![](../img/left_join.png)

        Arguments:
            other: another collection to join with
            mapping: a dictionary of **left-keys**:**right-keys** that explain how to join
            lsuffix: a suffix to add to the left keys in case of an overlap
            rsuffix: a suffix to add to the right keys in case of an overlap

        Usage:

        ```python
        from clumper import Clumper

        left = Clumper([
            {"a": 1, "b": 4},
            {"a": 2, "b": 6},
            {"a": 3, "b": 8},
        ])

        right = Clumper([
            {"c": 9, "b": 4},
            {"c": 8, "b": 5},
            {"c": 7, "b": 6},
        ])

        result = left.left_join(right, mapping={"b": "b"})
        expected = [
            {"a": 1, "b": 4, "c": 9},
            {"a": 2, "b": 6, "c": 7},
            {"a": 3, "b": 8},
        ]

        assert result.equals(expected)
        ```
        """
        result = []
        # This is a naive implementation. Speedup seems possible.
        for d_i in self:
            values_i = [d_i[k] for k in mapping.keys() if k in d_i.keys()]
            d_i_added = False
            for d_j in other:
                values_j = [d_j[k] for k in mapping.values() if k in d_j.keys()]
                if len(mapping) == len(values_i) == len(values_j):
                    if values_i == values_j:
                        result.append(
                            Clumper._merge_dicts(d_i, d_j, mapping, lsuffix, rsuffix)
                        )
                        d_i_added = True
            if not d_i_added:
                result.append(d_i)
        return self._create_new(result)

Performs a left join on two collections.

Each item from the left set will appear in the final collection. Only some items from the right set may appear if a merge is possible. There may be multiple copies of the left set if it can be joined multiple times.

Parameters

Name Type Description Default
other another collection to join with required
mapping a dictionary of left-keys:right-keys that explain how to join required
lsuffix a suffix to add to the left keys in case of an overlap ''
rsuffix a suffix to add to the right keys in case of an overlap '_joined'

Usage:

from clumper import Clumper

left = Clumper([
    {"a": 1, "b": 4},
    {"a": 2, "b": 6},
    {"a": 3, "b": 8},
])

right = Clumper([
    {"c": 9, "b": 4},
    {"c": 8, "b": 5},
    {"c": 7, "b": 6},
])

result = left.left_join(right, mapping={"b": "b"})
expected = [
    {"a": 1, "b": 4, "c": 9},
    {"a": 2, "b": 6, "c": 7},
    {"a": 3, "b": 8},
]

assert result.equals(expected)

map(self, func)

Show source code in clumper/clump.py
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
    def map(self, func):
        """
        Directly map one item to another one using a function.
        If you're dealing with dictionaries, consider using
        `mutate` instead.

        ![](../img/map.png)

        Arguments:
            func: the function that will map each item

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': 1}, {'a': 2}]

        (Clumper(list_dicts)
          .map(lambda d: {'a': d['a'], 'b': 1})
          .collect())
        ```
        """
        return self._create_new([func(d) for d in self.blob])

Directly map one item to another one using a function. If you're dealing with dictionaries, consider using mutate instead.

Parameters

Name Type Description Default
func the function that will map each item required

Usage:

from clumper import Clumper

list_dicts = [{'a': 1}, {'a': 2}]

(Clumper(list_dicts)
  .map(lambda d: {'a': d['a'], 'b': 1})
  .collect())

max(self, col)

Show source code in clumper/clump.py
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
    @dict_collection_only
    @return_value_if_empty(value=None)
    def max(self, col):
        """
        Returns maximum value that a key has.

        ![](../img/max.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert Clumper(list_of_dicts).max("a") == 7
        assert Clumper(list_of_dicts).max("b") == 7
        ```
        """
        return self.summarise_col("max", col)

Returns maximum value that a key has.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert Clumper(list_of_dicts).max("a") == 7
assert Clumper(list_of_dicts).max("b") == 7

mean(self, col)

Show source code in clumper/clump.py
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
    @dict_collection_only
    @return_value_if_empty(value=None)
    def mean(self, col):
        """
        Give the mean of the values that belong to a key.

        ![](../img/mean.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert round(Clumper(list_of_dicts).mean("a"), 1) == 3.5
        assert round(Clumper(list_of_dicts).mean("b"), 1) == 6.7
        ```
        """
        return self.summarise_col("mean", col)

Give the mean of the values that belong to a key.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert round(Clumper(list_of_dicts).mean("a"), 1) == 3.5
assert round(Clumper(list_of_dicts).mean("b"), 1) == 6.7

min(self, col)

Show source code in clumper/clump.py
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
    @dict_collection_only
    @return_value_if_empty(value=None)
    def min(self, col):
        """
        Returns minimum value that a key has.

        ![](../img/min.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert Clumper(list_of_dicts).min("a") == 2
        assert Clumper(list_of_dicts).min("b") == 6
        ```
        """
        return self.summarise_col("min", col)

Returns minimum value that a key has.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert Clumper(list_of_dicts).min("a") == 2
assert Clumper(list_of_dicts).min("b") == 6

mutate(self, **kwargs)

Show source code in clumper/clump.py
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
    @grouped
    def mutate(self, **kwargs):
        """
        Adds or overrides key-value pairs in the collection of dictionaries.

        ![](../img/mutate.png)

        Arguments:
            kwargs: keyword arguments of keyname/function-pairs

        Warning:
            This method is aware of groups. There may be different results if a group is active.

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [
            {'a': 1, 'b': 2},
            {'a': 2, 'b': 3, 'c':4},
            {'a': 1, 'b': 6}]

        result = (Clumper(list_dicts)
                  .mutate(c=lambda d: d['a'] + d['b'],
                          s=lambda d: d['a'] + d['b'] + d['c']))

        expected = [
            {'a': 1, 'b': 2, 'c': 3, 's': 6},
            {'a': 2, 'b': 3, 'c': 5, 's': 10},
            {'a': 1, 'b': 6, 'c': 7, 's': 14}
        ]

        assert result.equals(expected)
        ```
        """
        data = []
        for d in self.blob.copy():
            new = {k: v for k, v in d.items()}
            for key, func in kwargs.items():
                new[key] = func(new)
            data.append(new)
        return self._create_new(data)

Adds or overrides key-value pairs in the collection of dictionaries.

Parameters

Name Type Description Default
**kwargs keyword arguments of keyname/function-pairs {}

Warning

This method is aware of groups. There may be different results if a group is active.

Usage:

from clumper import Clumper

list_dicts = [
    {'a': 1, 'b': 2},
    {'a': 2, 'b': 3, 'c':4},
    {'a': 1, 'b': 6}]

result = (Clumper(list_dicts)
          .mutate(c=lambda d: d['a'] + d['b'],
                  s=lambda d: d['a'] + d['b'] + d['c']))

expected = [
    {'a': 1, 'b': 2, 'c': 3, 's': 6},
    {'a': 2, 'b': 3, 'c': 5, 's': 10},
    {'a': 1, 'b': 6, 'c': 7, 's': 14}
]

assert result.equals(expected)

n_unique(self, col)

Show source code in clumper/clump.py
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
    @dict_collection_only
    @return_value_if_empty(value=0)
    def n_unique(self, col):
        """
        Returns number of unique values that a key has.

        ![](../img/nunique.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert Clumper(list_of_dicts).n_unique("a") == 3
        assert Clumper(list_of_dicts).n_unique("b") == 2
        ```
        """
        return self.summarise_col("n_unique", col)

Returns number of unique values that a key has.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert Clumper(list_of_dicts).n_unique("a") == 3
assert Clumper(list_of_dicts).n_unique("b") == 2

pipe(self, func, *args, **kwargs)

Show source code in clumper/clump.py
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
    def pipe(self, func, *args, **kwargs):
        """
        Applies a function to the `Clumper` object in a chain-able manner.

        ![](../img/pipe.png)

        Arguments:
            func: function to apply
            args: arguments that will be passed to the function
            kwargs: keyword-arguments that will be passed to the function

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': i} for i in range(100)]

        def remove_outliers(clump, min_a, max_a):
            return (clump
                      .keep(lambda d: d['a'] >= min_a,
                            lambda d: d['a'] <= max_a))

        result = Clumper(list_dicts).pipe(remove_outliers, min_a=10, max_a=90)
        assert len(result) == 81
        ```
        """
        return func(self, *args, **kwargs)

Applies a function to the Clumper object in a chain-able manner.

Parameters

Name Type Description Default
func function to apply required
*args arguments that will be passed to the function ()
**kwargs keyword-arguments that will be passed to the function {}

Usage:

from clumper import Clumper

list_dicts = [{'a': i} for i in range(100)]

def remove_outliers(clump, min_a, max_a):
    return (clump
              .keep(lambda d: d['a'] >= min_a,
                    lambda d: d['a'] <= max_a))

result = Clumper(list_dicts).pipe(remove_outliers, min_a=10, max_a=90)
assert len(result) == 81

read_csv(path, delimiter=',', na_values=None, dtype=None, fieldnames=None, n=None) (classmethod)

Show source code in clumper/clump.py
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
    @classmethod
    @multifile()
    def read_csv(
        cls, path, delimiter=",", na_values=None, dtype=None, fieldnames=None, n=None
    ):
        """
        Reads in a csv file. Can also read files from url.

        ![](../img/read_csv.png)

        Arguments:
            path: Filename or url.
            delimiter: Delimiter used in the csv file. Must be a single character and `,` is the default.
            n: Number of rows to read in. Useful when reading large files. If `None`, all rows are read.
            fieldnames: Allows you to set the fieldnames if the header is missing. By default, the first
                        row of the csv will provide the Clumper keys if fieldnames is `None`. If fieldnames
                        is provided, then the first row becomes part of the data. You should ensure that
                        the correct number of fieldnames is supplied, as an incorrect number can lead
                        to an irregular outcome. If the row has seven fields and the number of fields in
                        fieldnames length is 3, then every row will have only 3 values, the remaining four
                        will be lumped into a list, and assigned key `None`. If the rows have fewer fields
                        than fieldnames, then the missing values are filled in with `None`.
            na_values:  This provides an option for treating null values. If `ignore`, null values are
                        returned as empty strings (""). If `None`, then for each row, the key,value pair
                        with the null values  will be truncated from the row. The only values treated as
                        null are empty strings("") and "NA".
            dtype: Data type for each value in a key:value pair. If `None`, then values will be read in as strings.
                   Available dtypes are (int, float, str). If a single dtype is passed, then all values will be
                   converted to the data type and raise an error, if not applicable. For different data types for different
                   key, value pairs, a dictionary of {key: data_type} passed to dtype argument will change the value for
                   every key with the data type, and raise an error if not applicable.

        Usage:

        ```python
        from clumper import Clumper

        clump = Clumper.read_csv("tests/data/monopoly.csv")
        assert len(clump) == 22

        clump = Clumper.read_csv("tests/data/monopoly.csv", n = 10)
        assert len(clump) == 10

        clump = Clumper.read_csv("https://calmcode.io/datasets/monopoly.csv")
        assert len(clump) == 22

        # If the fieldnames argument is not None, then the first row becomes part of the data.
        fieldnames = ['date', 'currency', 'country', 'price', 'dollar_rate', 'cost']
        clump = Clumper.read_csv("https://calmcode.io/datasets/bigmac.csv", fieldnames=fieldnames)

        first_row = ['date', 'currency_code','name','local_price', 'dollar_ex', 'dollar_price']
        assert clump.head(1).equals([dict(zip(fieldnames, first_row))])
        ```
        """
        if n is not None:
            if n <= 0:
                raise ValueError("Number of lines to read must be > 0.")

        # conveniently excludes pathlib files here and removes
        # the need to write code to check pathlib files in other places.
        if isinstance(path, str) and path.startswith(("https:", "http:")):
            with urllib.request.urlopen(path) as resp:
                if fieldnames is None:
                    fieldnames = resp.readline().decode().strip().split(",")
                # This section allows us to chunk the rows, if nrows is supplied.
                body = it.islice(resp, 0, n)
                body = (word.decode().strip().split(",") for word in body)
                body = it.product([fieldnames], body)
                result = [dict(zip(key, values)) for key, values in body]
        else:
            with open(path, newline="") as csvfile:
                reader = csv.DictReader(
                    csvfile, delimiter=delimiter, fieldnames=fieldnames
                )
                # python version less than 3.8 returns an OrderedDict
                result = [dict(entry) for entry in it.islice(reader, 0, n)]

        # Null values, same as missing keys.
        # If there are null values/missing keys, they will be truncated from the dictionary.
        # Python's csv module treats null values as empty strings when writing to a csv -
        # https://docs.python.org/3.8/library/csv.html#csv.DictWriter.
        # The user can choose to explicitly show missing keys/null values in the dictionary,
        # by assigning `ignore` to the na_values argument. At the moment, the default for
        # null values are empty string ("") and "NA".

        if na_values == "ignore":
            result = result
        else:
            na_values = ["", "NA"]
            result = [
                {key: value for key, value in entry.items() if value not in na_values}
                for entry in result
            ]

        # The csv module reads every row as a string, there are no data type assumptions.
        # This function attempts to solve this. The user can pass a string of either
        # ('int', 'str', 'float') or if the user knows the keys/fieldnames, can pass a
        # dictionary mapping the key to the data type.
        # Technically 'str' data type is not needed, since data is read in as strings anyway.

        if not (isinstance(dtype, (dict, str)) or dtype is None):
            raise TypeError(
                """dtype should be a dictionary pair of key and data type, or a single string data type"""
            )

        dtype_mapping = {"int": int, "float": float, "str": str}
        if dtype:
            if isinstance(dtype, str) and dtype in ("int", "float", "str"):
                result = [
                    {key: dtype_mapping[dtype](value) for key, value in entry.items()}
                    for entry in result
                ]
            else:
                result = [
                    {
                        key: dtype_mapping[dtype[key]](value) if key in dtype else value
                        for key, value in entry.items()
                    }
                    for entry in result
                ]

        return Clumper(result)

Reads in a csv file. Can also read files from url.

Parameters

Name Type Description Default
path Filename or url. required
delimiter Delimiter used in the csv file. Must be a single character and , is the default. ','
n Number of rows to read in. Useful when reading large files. If None, all rows are read. None
fieldnames Allows you to set the fieldnames if the header is missing. By default, the first row of the csv will provide the Clumper keys if fieldnames is None. If fieldnames is provided, then the first row becomes part of the data. You should ensure that the correct number of fieldnames is supplied, as an incorrect number can lead to an irregular outcome. If the row has seven fields and the number of fields in fieldnames length is 3, then every row will have only 3 values, the remaining four will be lumped into a list, and assigned key None. If the rows have fewer fields than fieldnames, then the missing values are filled in with None. None
na_values This provides an option for treating null values. If ignore, null values are returned as empty strings (""). If None, then for each row, the key,value pair with the null values will be truncated from the row. The only values treated as null are empty strings("") and "NA". None
dtype Data type for each value in a key:value pair. If None, then values will be read in as strings. Available dtypes are (int, float, str). If a single dtype is passed, then all values will be converted to the data type and raise an error, if not applicable. For different data types for different key, value pairs, a dictionary of {key: data_type} passed to dtype argument will change the value for every key with the data type, and raise an error if not applicable. None

Usage:

from clumper import Clumper

clump = Clumper.read_csv("tests/data/monopoly.csv")
assert len(clump) == 22

clump = Clumper.read_csv("tests/data/monopoly.csv", n = 10)
assert len(clump) == 10

clump = Clumper.read_csv("https://calmcode.io/datasets/monopoly.csv")
assert len(clump) == 22

# If the fieldnames argument is not None, then the first row becomes part of the data.
fieldnames = ['date', 'currency', 'country', 'price', 'dollar_rate', 'cost']
clump = Clumper.read_csv("https://calmcode.io/datasets/bigmac.csv", fieldnames=fieldnames)

first_row = ['date', 'currency_code','name','local_price', 'dollar_ex', 'dollar_price']
assert clump.head(1).equals([dict(zip(fieldnames, first_row))])

read_json(path, n=None) (classmethod)

Show source code in clumper/clump.py
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
    @classmethod
    @multifile()
    def read_json(cls, path, n=None):
        """
        Reads in a json file. Can also read files from url.

        ![](../img/read_json.png)

        Arguments:
            path: filename or url. Filenames can include a wildcard `*`.
            n: Number of rows to read in. Useful when reading large files. If `None`, all rows are read.

        Usage:

        ```python
        from clumper import Clumper

        clump = Clumper.read_json("tests/data/pokemon.json")
        assert len(clump) == 800

        clump = Clumper.read_json("https://calmcode.io/datasets/got.json")
        assert len(clump) == 30

        clump = Clumper.read_json("https://calmcode.io/datasets/got.json", n=10)
        assert len(clump) == 10
        ```
        """
        if n is not None:
            if n <= 0:
                raise ValueError("Number of lines to read must be > 0.")

        if path.startswith("https:") or path.startswith("http:"):
            with urllib.request.urlopen(path) as resp:
                data = json.loads(resp.read())
        else:
            data = json.loads(pathlib.Path(path).read_text())
        if n:
            return Clumper(list(it.islice(data, 0, n)))
        return Clumper(data)

Reads in a json file. Can also read files from url.

Parameters

Name Type Description Default
path filename or url. Filenames can include a wildcard *. required
n Number of rows to read in. Useful when reading large files. If None, all rows are read. None

Usage:

from clumper import Clumper

clump = Clumper.read_json("tests/data/pokemon.json")
assert len(clump) == 800

clump = Clumper.read_json("https://calmcode.io/datasets/got.json")
assert len(clump) == 30

clump = Clumper.read_json("https://calmcode.io/datasets/got.json", n=10)
assert len(clump) == 10

read_jsonl(path, n=None) (classmethod)

Show source code in clumper/clump.py
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
    @classmethod
    @multifile()
    def read_jsonl(cls, path, n=None):
        """
        Reads in a jsonl file. Can also read files from url.

        ![](../img/read_jsonl.png)

        Arguments:
            path: filename or url. Filenames can include a wildcard `*`.
            n: Number of rows to read in. Useful when reading large files. If `None`, all rows are read.

        Usage:

        ```python
        from clumper import Clumper

        clump = Clumper.read_jsonl("tests/data/cards.jsonl")
        assert len(clump) == 4

        clump = Clumper.read_jsonl("https://calmcode.io/datasets/pokemon.jsonl")
        assert len(clump) == 800

        clump = Clumper.read_jsonl("https://calmcode.io/datasets/pokemon.jsonl", n=10)
        assert len(clump) == 10
        ```
        """
        if n is not None:
            if n <= 0:
                raise ValueError("Number of lines to read must be > 0.")

        # Case 1 : Open cloud file in stream
        if path.startswith("https:") or path.startswith("http:"):
            f = urllib.request.urlopen(path)
        # Case 2 : Local file
        else:
            f = open(path)

        # Initialize a place to store the parsed data as list
        data_array = []
        # Read it, parse and close it
        with f:
            for current_line_nr, json_string in enumerate(f):
                if n is not None and current_line_nr == n:
                    break
                json_object = json.loads(json_string)
                data_array.append(json_object)
        # Return it
        return Clumper(data_array)

Reads in a jsonl file. Can also read files from url.

Parameters

Name Type Description Default
path filename or url. Filenames can include a wildcard *. required
n Number of rows to read in. Useful when reading large files. If None, all rows are read. None

Usage:

from clumper import Clumper

clump = Clumper.read_jsonl("tests/data/cards.jsonl")
assert len(clump) == 4

clump = Clumper.read_jsonl("https://calmcode.io/datasets/pokemon.jsonl")
assert len(clump) == 800

clump = Clumper.read_jsonl("https://calmcode.io/datasets/pokemon.jsonl", n=10)
assert len(clump) == 10

read_yaml(path, n=None) (classmethod)

Show source code in clumper/clump.py
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
    @classmethod
    @multifile()
    def read_yaml(cls, path: str, n=None):
        """
        Reads in a yaml file.

        ![](../img/read_yaml.png)

        Arguments:
            path: filename or url. Filenames can include a wildcard `*`.
            n: number of lines to read in, if `None` will read all

        Important:
            This method requires the `PyYAML` dependency which is not installed automatically.
            To install it you can run;

            ```
            # This will only install the yaml dependencies.
            pip install clumper[yaml]
            # This will install all optional dependencies.
            pip install clumper[all]
            ```

        Usage:

        ```python
        from clumper import Clumper

        clump = Clumper.read_yaml("tests/data/demo-flat-1.yaml")
        assert len(clump) == 3

        clump = Clumper.read_yaml("tests/data/*.yaml")
        assert len(clump) == 6
        ```
        """
        # Case 1 : Open cloud file in stream
        if path.startswith(("https:", "http:")):
            f = urllib.request.urlopen(path)
        # Case 2 : Local file
        else:
            f = open(path)

        # Try to load it but tell the user to install if not there.
        try:
            import yaml

            data = yaml.load(f.read(), Loader=yaml.FullLoader)
            return Clumper(list(it.islice(data, 0, n)))
        except ImportError:
            raise_yaml_dep_error()

Reads in a yaml file.

Parameters

Name Type Description Default
path str filename or url. Filenames can include a wildcard *. required
n number of lines to read in, if None will read all None

Important

This method requires the PyYAML dependency which is not installed automatically. To install it you can run;

# This will only install the yaml dependencies.
pip install clumper[yaml]
# This will install all optional dependencies.
pip install clumper[all]

Usage:

from clumper import Clumper

clump = Clumper.read_yaml("tests/data/demo-flat-1.yaml")
assert len(clump) == 3

clump = Clumper.read_yaml("tests/data/*.yaml")
assert len(clump) == 6

reduce(self, **kwargs)

Show source code in clumper/clump.py
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
    def reduce(self, **kwargs):
        """
        Reduce the collection using reducing functions.

        ![](../img/reduce.png)

        Arguments:
            kwargs: key-function pairs

        Usage:

        ```python
        from clumper import Clumper

        list_ints = [1, 2, 3, 4, 5]

        (Clumper(list_ints)
          .reduce(sum_a = lambda x,y: x + y,
                  min_a = lambda x,y: min(x, y),
                  max_a = lambda x,y: max(x, y))
          .collect())
        ```
        """
        return self._create_new(
            [{k: reduce(func, [b for b in self.blob]) for k, func in kwargs.items()}]
        )

Reduce the collection using reducing functions.

Parameters

Name Type Description Default
**kwargs key-function pairs {}

Usage:

from clumper import Clumper

list_ints = [1, 2, 3, 4, 5]

(Clumper(list_ints)
  .reduce(sum_a = lambda x,y: x + y,
          min_a = lambda x,y: min(x, y),
          max_a = lambda x,y: max(x, y))
  .collect())

rename(self, **kwargs)

Show source code in clumper/clump.py
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
    def rename(self, **kwargs):
        """
        Rename items in the collection.

        Usage:

        ```python
        from clumper import Clumper

        data = [{'a': 1, 'b': 3}, {'a': 2, 'b': 4}]

        clumper = Clumper(data).rename(c="b")
        expected = [{'a': 1, 'c': 3}, {'a': 2, 'c': 4}]
        assert clumper.equals(expected)
        ```
        """
        result = self.copy()
        for new_name, old_name in kwargs.items():
            result = result.mutate(**{new_name: lambda d: d[old_name]}).drop(old_name)
        return result

Rename items in the collection.

Usage:

from clumper import Clumper

data = [{'a': 1, 'b': 3}, {'a': 2, 'b': 4}]

clumper = Clumper(data).rename(c="b")
expected = [{'a': 1, 'c': 3}, {'a': 2, 'c': 4}]
assert clumper.equals(expected)

select(self, *keys)

Show source code in clumper/clump.py
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
    @dict_collection_only
    def select(self, *keys):
        """
        Selects a subset of the keys in each item in the collection.

        ![](../img/select.png)

        Arguments:
            keys: the keys to keep

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [
            {'a': 1, 'b': 2},
            {'a': 2, 'b': 3, 'c':4},
            {'a': 1, 'b': 6}]

        clump = Clumper(list_dicts).select('a', 'b')
        assert all(["c" not in d.keys() for d in clump])
        ```
        """
        return self._create_new([{k: d[k] for k in keys} for d in self.blob])

Selects a subset of the keys in each item in the collection.

Parameters

Name Type Description Default
*keys the keys to keep ()

Usage:

from clumper import Clumper

list_dicts = [
    {'a': 1, 'b': 2},
    {'a': 2, 'b': 3, 'c':4},
    {'a': 1, 'b': 6}]

clump = Clumper(list_dicts).select('a', 'b')
assert all(["c" not in d.keys() for d in clump])

sort(self, key, reverse=False)

Show source code in clumper/clump.py
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
    @grouped
    def sort(self, key, reverse=False):
        """
        Allows you to sort the collection of dictionaries.

        ![](../img/sort.png)

        Arguments:
            key: the number of items to grab
            reverse: the number of items to grab

        Warning:
            This method is aware of groups. Expect different results if a group is active.

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [
            {'a': 1, 'b': 2},
            {'a': 3, 'b': 3},
            {'a': 2, 'b': 1}]

        (Clumper(list_dicts)
          .sort(lambda d: d['a'])
          .collect())

        (Clumper(list_dicts)
          .sort(lambda d: d['b'], reverse=True)
          .collect())
        ```
        """
        return self._create_new(sorted(self.blob, key=key, reverse=reverse))

Allows you to sort the collection of dictionaries.

Parameters

Name Type Description Default
key the number of items to grab required
reverse the number of items to grab False

Warning

This method is aware of groups. Expect different results if a group is active.

Usage:

from clumper import Clumper

list_dicts = [
    {'a': 1, 'b': 2},
    {'a': 3, 'b': 3},
    {'a': 2, 'b': 1}]

(Clumper(list_dicts)
  .sort(lambda d: d['a'])
  .collect())

(Clumper(list_dicts)
  .sort(lambda d: d['b'], reverse=True)
  .collect())

sum(self, col)

Show source code in clumper/clump.py
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
    @dict_collection_only
    @return_value_if_empty(value=None)
    def sum(self, col):
        """
        Give the sum of the values that belong to a key.

        ![](../img/sum.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        Clumper(list_of_dicts).sum("a")
        Clumper(list_of_dicts).sum("b")
        ```
        """
        return self.summarise_col("sum", col)

Give the sum of the values that belong to a key.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

Clumper(list_of_dicts).sum("a")
Clumper(list_of_dicts).sum("b")

summarise_col(self, func, key)

Show source code in clumper/clump.py
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
    def summarise_col(self, func, key):
        """
        Apply your own summary function to a key in the collection.

        It can also accept a string and it will try to fetch an appropriate function
        for you. If you pass a string it must be either: `mean`, `count`, `unique`,
        `n_unique`, `sum`, `min`, `max`, `median`, `values`, `var`, `std`, `first` or `last`.

        Note that this method **ignores groups**. It also does not return a `Clumper`
        collection.

        Usage:

        ```python
        from clumper import Clumper

        clump = Clumper([{"a": 1}, {"a": 2}, {"a": 3}])

        assert clump.summarise_col("last", "a") == 3
        assert clump.summarise_col(lambda d: d[-1], "a") == 3
        ```
        """
        funcs = {
            "mean": mean,
            "count": lambda d: len(d),
            "unique": lambda d: list(set(d)),
            "n_unique": lambda d: len(set(d)),
            "sum": sum,
            "min": min,
            "max": max,
            "median": median,
            "var": variance,
            "std": stdev,
            "values": lambda d: d,
            "first": lambda d: d[0],
            "last": lambda d: d[-1],
        }
        if isinstance(func, str):
            if func not in funcs.keys():
                raise ValueError(
                    f"Passed `func` must be in {funcs.keys()}, got {func}."
                )
            func = funcs[func]
        array = [d[key] for d in self if key in d.keys()]
        return func(array)

Apply your own summary function to a key in the collection.

It can also accept a string and it will try to fetch an appropriate function for you. If you pass a string it must be either: mean, count, unique, n_unique, sum, min, max, median, values, var, std, first or last.

Note that this method ignores groups. It also does not return a Clumper collection.

Usage:

from clumper import Clumper

clump = Clumper([{"a": 1}, {"a": 2}, {"a": 3}])

assert clump.summarise_col("last", "a") == 3
assert clump.summarise_col(lambda d: d[-1], "a") == 3

tail(self, n=5)

Show source code in clumper/clump.py
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
    def tail(self, n=5):
        """
        Selects the bottom `n` items from the collection.

        ![](../img/tail.png)

        Arguments:
            n: the number of items to grab

        Usage:

        ```python
        from clumper import Clumper

        list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

        result = Clumper(list_dicts).tail(2)
        expected = [{'a': 3}, {'a': 4}]
        assert result.equals(expected)
        ```
        """
        if not isinstance(n, int):
            raise ValueError(f"`n` must be a positive integer, got {n}")
        if n < 0:
            raise ValueError(f"`n` must be positive, got {n}")
        n = min(n, len(self))
        return self._create_new(self.blob[len(self) - n : len(self)])

Selects the bottom n items from the collection.

Parameters

Name Type Description Default
n the number of items to grab 5

Usage:

from clumper import Clumper

list_dicts = [{'a': 1}, {'a': 2}, {'a': 3}, {'a': 4}]

result = Clumper(list_dicts).tail(2)
expected = [{'a': 3}, {'a': 4}]
assert result.equals(expected)

transform(self, **kwargs)

Show source code in clumper/clump.py
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
    @grouped
    @dict_collection_only
    def transform(self, **kwargs):
        """
        Does an aggregation just like `.agg()` however instead of reducing the rows we
        merge the results back with the original data. This saves a lot of compute time
        because effectively this prevents us from performing a join.

        ![](../img/transform-with-groups.png)

        Arguments:
            kwargs: keyword arguments that represent the aggregation that is about to happen, see usage below.

        Warning:
            This method is aware of groups. There may be different results if a group is active.

        Usage:

        ```python
        from clumper import Clumper

        data = [
            {"a": 6, "grp": "a"},
            {"a": 2, "grp": "b"},
            {"a": 7, "grp": "a"},
            {"a": 9, "grp": "b"},
            {"a": 5, "grp": "a"}
        ]

        tfm_clump = (Clumper(data)
                      .group_by("grp")
                      .transform(s=("a", "sum"),
                                 u=("a", "unique")))

        expected = [
            {'a': 6, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 7, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 5, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
            {'a': 2, 'grp': 'b', 's': 11, 'u': [9, 2]},
            {'a': 9, 'grp': 'b', 's': 11, 'u': [9, 2]}
        ]

        assert tfm_clump.equals(expected)
        ```
        """
        agg_results = self.agg(**kwargs)
        return self.left_join(agg_results, mapping={k: k for k in self.groups})

Does an aggregation just like .agg() however instead of reducing the rows we merge the results back with the original data. This saves a lot of compute time because effectively this prevents us from performing a join.

Parameters

Name Type Description Default
**kwargs keyword arguments that represent the aggregation that is about to happen, see usage below. {}

Warning

This method is aware of groups. There may be different results if a group is active.

Usage:

from clumper import Clumper

data = [
    {"a": 6, "grp": "a"},
    {"a": 2, "grp": "b"},
    {"a": 7, "grp": "a"},
    {"a": 9, "grp": "b"},
    {"a": 5, "grp": "a"}
]

tfm_clump = (Clumper(data)
              .group_by("grp")
              .transform(s=("a", "sum"),
                         u=("a", "unique")))

expected = [
    {'a': 6, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 7, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 5, 'grp': 'a', 's': 18, 'u': [5, 6, 7]},
    {'a': 2, 'grp': 'b', 's': 11, 'u': [9, 2]},
    {'a': 9, 'grp': 'b', 's': 11, 'u': [9, 2]}
]

assert tfm_clump.equals(expected)

ungroup(self)

Show source code in clumper/clump.py
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
    def ungroup(self):
        """
        Removes all grouping from the collection.

        ![](../img/ungroup.png)

        ```python
        from clumper import Clumper

        clump = Clumper([{"a": 1}]).group_by("a")
        assert clump.groups == ("a", )
        assert clump.ungroup().groups == tuple()
        ```
        """
        self.groups = tuple()
        return self

Removes all grouping from the collection.

from clumper import Clumper

clump = Clumper([{"a": 1}]).group_by("a")
assert clump.groups == ("a", )
assert clump.ungroup().groups == tuple()

unique(self, col)

Show source code in clumper/clump.py
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
    @dict_collection_only
    @return_value_if_empty(value=[])
    def unique(self, col):
        """
        Returns a set of unique values that a key has.

        ![](../img/unique.png)

        Usage:

        ```python
        from clumper import Clumper

        list_of_dicts = [
            {'a': 7},
            {'a': 2, 'b': 7},
            {'a': 3, 'b': 6},
            {'a': 2, 'b': 7}
        ]

        assert Clumper(list_of_dicts).unique("a") == [2, 3, 7]
        assert Clumper(list_of_dicts).unique("b") == [6, 7]
        ```
        """
        return self.summarise_col("unique", col)

Returns a set of unique values that a key has.

Usage:

from clumper import Clumper

list_of_dicts = [
    {'a': 7},
    {'a': 2, 'b': 7},
    {'a': 3, 'b': 6},
    {'a': 2, 'b': 7}
]

assert Clumper(list_of_dicts).unique("a") == [2, 3, 7]
assert Clumper(list_of_dicts).unique("b") == [6, 7]

write_csv(self, path, mode='w')

Show source code in clumper/clump.py
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
    def write_csv(self, path, mode="w"):
        """
        Write to a csv file.

        Arguments:
        path: filename
        mode: `w` writes to a file if it does not exist, or overwrites if it already exists,
               while `a`: - append to file if it already exists. The default is `w`.

        Note that null values will be exported as empty strings; this is the convention chosen by Python.

        Usage:

        ```python
        from clumper import Clumper
        from pathlib import Path
        path = '/tmp/monopoly.csv'
        Clumper.read_csv("tests/data/monopoly.csv").write_csv(path)
        reader = Clumper.read_csv(path)
        assert Clumper.read_csv("tests/data/monopoly.csv").collect() == reader.collect()
        ```
        """

        with open(path, mode=mode, newline="") as csvfile:
            fieldnames = self.keys()
            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

            writer.writeheader()

            for row in self:
                writer.writerow(row)

Write to a csv file.

Parameters

Name Type Description Default

path: filename mode: w writes to a file if it does not exist, or overwrites if it already exists, while a: - append to file if it already exists. The default is w.

Note that null values will be exported as empty strings; this is the convention chosen by Python.

Usage:

from clumper import Clumper
from pathlib import Path
path = '/tmp/monopoly.csv'
Clumper.read_csv("tests/data/monopoly.csv").write_csv(path)
reader = Clumper.read_csv(path)
assert Clumper.read_csv("tests/data/monopoly.csv").collect() == reader.collect()

write_json(self, path, sort_keys=False, indent=None)

Show source code in clumper/clump.py
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
    def write_json(self, path, sort_keys=False, indent=None):
        """
        Writes to a json file.

        Arguments:
            path: filename
            sort_keys: If sort_keys is true (default: False), then the output of dictionaries will be sorted by key.
            indent: If indent is a non-negative integer (default: None), then JSON array elements members will be pretty-printed with that indent level.

        Usage:

        ```python
        from clumper import Clumper
        clump_orig = Clumper.read_json("tests/data/pokemon.json")
        clump_orig.write_json("tests/data/pokemon_copy.json")

        clump_copy = Clumper.read_json("tests/data/pokemon_copy.json")
        assert clump_copy.collect() == clump_orig.collect()
        ```
        """
        # Create a new file and open it for writing
        with open(path, "w") as f:
            json.dump(self.collect(), f, sort_keys=sort_keys, indent=indent)

Writes to a json file.

Parameters

Name Type Description Default
path filename required
sort_keys If sort_keys is true (default: False), then the output of dictionaries will be sorted by key. False
indent If indent is a non-negative integer (default: None), then JSON array elements members will be pretty-printed with that indent level. None

Usage:

from clumper import Clumper
clump_orig = Clumper.read_json("tests/data/pokemon.json")
clump_orig.write_json("tests/data/pokemon_copy.json")

clump_copy = Clumper.read_json("tests/data/pokemon_copy.json")
assert clump_copy.collect() == clump_orig.collect()

write_jsonl(self, path, sort_keys=False, indent=None)

Show source code in clumper/clump.py
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
    def write_jsonl(self, path, sort_keys=False, indent=None):
        """
        Writes to a jsonl file.

        Arguments:
            path: filename
            sort_keys: If sort_keys is true (default: False), then the output of dictionaries will be sorted by key.
            indent: If indent is a non-negative integer (default: None), then JSON array elements members will be pretty-printed with that indent level.
        """
        # Create a new file and open it for writing
        with open(path, "x") as f:
            for current_line_nr, json_dict in enumerate(self.collect()):
                f.write(
                    json.dumps(json_dict, sort_keys=sort_keys, indent=indent) + "\n"
                )

Writes to a jsonl file.

Parameters

Name Type Description Default
path filename required
sort_keys If sort_keys is true (default: False), then the output of dictionaries will be sorted by key. False
indent If indent is a non-negative integer (default: None), then JSON array elements members will be pretty-printed with that indent level. None

write_yaml(self, path)

Show source code in clumper/clump.py
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
    def write_yaml(self, path):
        """
        Write the collection of data as a yaml file.

        Arguments:
            path: path to write the file to

        Important:
            This method requires the `PyYAML` dependency which is not installed automatically.
            To install it you can run;

            ```
            # This will only install the yaml dependencies.
            pip install clumper[yaml]
            # This will install all optional dependencies.
            pip install clumper[all]
            ```

        Usage:

        ```python
        from clumper import Clumper
        clump_orig = Clumper.read_yaml("tests/data/demo-flat-1.yaml")
        clump_orig.write_json("tests/data/demo-flat-copy.json")

        clump_copy = Clumper.read_json("tests/data/demo-flat-copy.json")
        assert clump_copy.collect() == clump_orig.collect()
        ```
        """
        try:
            import yaml

            with open(path, "x") as f:
                txt = yaml.dump(self.collect())
                f.write(txt)
        except ImportError:
            raise_yaml_dep_error()

Write the collection of data as a yaml file.

Parameters

Name Type Description Default
path path to write the file to required

Important

This method requires the PyYAML dependency which is not installed automatically. To install it you can run;

# This will only install the yaml dependencies.
pip install clumper[yaml]
# This will install all optional dependencies.
pip install clumper[all]

Usage:

from clumper import Clumper
clump_orig = Clumper.read_yaml("tests/data/demo-flat-1.yaml")
clump_orig.write_json("tests/data/demo-flat-copy.json")

clump_copy = Clumper.read_json("tests/data/demo-flat-copy.json")
assert clump_copy.collect() == clump_orig.collect()