X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=histogram.py;h=86d0493dc57e32056c4eb04ec4499992d365e542;hb=02302bbd9363facb59c4df2c1f4013087702cfa6;hp=52a0d1fad558a493c6e303abdd07a6933053a045;hpb=532df2c5b57c7517dfb3dddd8c1358fbadf8baf3;p=python_utils.git diff --git a/histogram.py b/histogram.py index 52a0d1f..86d0493 100644 --- a/histogram.py +++ b/histogram.py @@ -19,11 +19,22 @@ class BucketDetails: """A collection of details about the internal histogram buckets.""" num_populated_buckets: int = 0 + """Count of populated buckets""" + max_population: Optional[int] = None + """The max population in a bucket currently""" + last_bucket_start: Optional[int] = None + """The last bucket starting point""" + lowest_start: Optional[int] = None + """The lowest populated bucket's starting point""" + highest_end: Optional[int] = None + """The highest populated bucket's ending point""" + max_label_width: Optional[int] = None + """The maximum label width (for display purposes)""" class SimpleHistogram(Generic[T]): @@ -34,6 +45,14 @@ class SimpleHistogram(Generic[T]): NEGATIVE_INFINITY = -math.inf def __init__(self, buckets: List[Tuple[Bound, Bound]]): + """C'tor. + + Args: + buckets: a list of [start..end] tuples that define the + buckets we are counting population in. See also + :meth:`n_evenly_spaced_buckets` to generate these + buckets more easily. + """ from math_utils import NumericPopulation self.buckets: Dict[Tuple[Bound, Bound], Count] = {} @@ -53,6 +72,17 @@ class SimpleHistogram(Generic[T]): max_bound: T, n: int, ) -> List[Tuple[int, int]]: + """A helper method for generating the buckets argument to + our c'tor provided that you want N evenly spaced buckets. + + Args: + min_bound: the minimum possible value + max_bound: the maximum possible value + n: how many buckets to create + + Returns: + A list of bounds that define N evenly spaced buckets + """ ret: List[Tuple[int, int]] = [] stride = int((max_bound - min_bound) / n) if stride <= 0: @@ -64,12 +94,23 @@ class SimpleHistogram(Generic[T]): return ret def _get_bucket(self, item: T) -> Optional[Tuple[int, int]]: + """Given an item, what bucket is it in?""" for start_end in self.buckets: if start_end[0] <= item < start_end[1]: return start_end return None def add_item(self, item: T) -> bool: + """Adds a single item to the histogram (reculting in us incrementing + the population in the correct bucket. + + Args: + item: the item to be added + + Returns: + True if the item was successfully added or False if the item + is not within the bounds established during class construction. + """ bucket = self._get_bucket(item) if bucket is None: return False @@ -84,12 +125,24 @@ class SimpleHistogram(Generic[T]): return True def add_items(self, lst: Iterable[T]) -> bool: + """Adds a collection of items to the histogram and increments + the correct bucket's population for each item. + + Args: + lst: An iterable of items to be added + + Returns: + True if all items were added successfully or False if any + item was not able to be added because it was not within the + bounds established at object construction. + """ all_true = True for item in lst: all_true = all_true and self.add_item(item) return all_true - def get_bucket_details(self, label_formatter: str) -> BucketDetails: + def _get_bucket_details(self, label_formatter: str) -> BucketDetails: + """Get the details about one bucket.""" details = BucketDetails() for (start, end), pop in sorted(self.buckets.items(), key=lambda x: x[0]): if pop > 0: @@ -108,9 +161,13 @@ class SimpleHistogram(Generic[T]): return details def __repr__(self, *, width: int = 80, label_formatter: str = '%d') -> str: + """Returns a pretty (text) representation of the histogram and + some vital stats about the population in it (min, max, mean, + median, mode, stdev, etc...) + """ from text_utils import bar_graph - details = self.get_bucket_details(label_formatter) + details = self._get_bucket_details(label_formatter) txt = "" if details.num_populated_buckets == 0: return txt