[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

DIRECTORY.md

@@ -710,6 +710,7 @@
   * [2 Hidden Layers Neural Network](neural_network/2_hidden_layers_neural_network.py)
   * Activation Functions
     * [Exponential Linear Unit](neural_network/activation_functions/exponential_linear_unit.py)
+    * [Leaky Rectified Linear Unit](neural_network/activation_functions/leaky_rectified_linear_unit.py)
   * [Back Propagation Neural Network](neural_network/back_propagation_neural_network.py)
   * [Convolution Neural Network](neural_network/convolution_neural_network.py)
   * [Perceptron](neural_network/perceptron.py)
@@ -1212,6 +1213,7 @@
   * [Daily Horoscope](web_programming/daily_horoscope.py)
   * [Download Images From Google Query](web_programming/download_images_from_google_query.py)
   * [Emails From Url](web_programming/emails_from_url.py)
+  * [Fetch Anime And Play](web_programming/fetch_anime_and_play.py)
   * [Fetch Bbc News](web_programming/fetch_bbc_news.py)
   * [Fetch Github Info](web_programming/fetch_github_info.py)
   * [Fetch Jobs](web_programming/fetch_jobs.py)
@@ -1220,6 +1222,7 @@
   * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
   * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
   * [Get Imdbtop](web_programming/get_imdbtop.py)
+  * [Get Top Billionaires](web_programming/get_top_billionaires.py)
   * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
   * [Get User Tweets](web_programming/get_user_tweets.py)
   * [Giphy](web_programming/giphy.py)

linear_programming/simplex.py

@@ -20,40 +20,60 @@ import numpy as np
 class Tableau:
     """Operate on simplex tableaus
 
-    >>> t = Tableau(np.array([[-1,-1,0,0,-1],[1,3,1,0,4],[3,1,0,1,4.]]), 2)
+    >>> Tableau(np.array([[-1,-1,0,0,1],[1,3,1,0,4],[3,1,0,1,4]]), 2, 2)
+    Traceback (most recent call last):
+    ...
+    TypeError: Tableau must have type float64
+
+    >>> Tableau(np.array([[-1,-1,0,0,-1],[1,3,1,0,4],[3,1,0,1,4.]]), 2, 2)
     Traceback (most recent call last):
     ...
     ValueError: RHS must be > 0
+
+    >>> Tableau(np.array([[-1,-1,0,0,1],[1,3,1,0,4],[3,1,0,1,4.]]), -2, 2)
+    Traceback (most recent call last):
+    ...
+    ValueError: number of (artificial) variables must be a natural number
     """
 
-    def __init__(self, tableau: np.ndarray, n_vars: int) -> None:
+    # Max iteration number to prevent cycling
+    maxiter = 100
+
+    def __init__(
+        self, tableau: np.ndarray, n_vars: int, n_artificial_vars: int
+    ) -> None:
+        if tableau.dtype != "float64":
+            raise TypeError("Tableau must have type float64")
+
         # Check if RHS is negative
-        if np.any(tableau[:, -1], where=tableau[:, -1] < 0):
+        if not (tableau[:, -1] >= 0).all():
             raise ValueError("RHS must be > 0")
 
+        if n_vars < 2 or n_artificial_vars < 0:
+            raise ValueError(
+                "number of (artificial) variables must be a natural number"
+            )
+
         self.tableau = tableau
-        self.n_rows, _ = tableau.shape
+        self.n_rows, n_cols = tableau.shape
 
         # Number of decision variables x1, x2, x3...
-        self.n_vars = n_vars
+        self.n_vars, self.n_artificial_vars = n_vars, n_artificial_vars
-
-        # Number of artificial variables to be minimised
-        self.n_art_vars = len(np.where(tableau[self.n_vars : -1] == -1)[0])
 
         # 2 if there are >= or == constraints (nonstandard), 1 otherwise (std)
-        self.n_stages = (self.n_art_vars > 0) + 1
+        self.n_stages = (self.n_artificial_vars > 0) + 1
 
         # Number of slack variables added to make inequalities into equalities
-        self.n_slack = self.n_rows - self.n_stages
+        self.n_slack = n_cols - self.n_vars - self.n_artificial_vars - 1
 
         # Objectives for each stage
         self.objectives = ["max"]
 
         # In two stage simplex, first minimise then maximise
-        if self.n_art_vars:
+        if self.n_artificial_vars:
             self.objectives.append("min")
 
-        self.col_titles = [""]
+        self.col_titles = self.generate_col_titles()
 
         # Index of current pivot row and column
         self.row_idx = None
@@ -62,48 +82,39 @@ class Tableau:
         # Does objective row only contain (non)-negative values?
         self.stop_iter = False
 
-    @staticmethod
+    def generate_col_titles(self) -> list[str]:
-    def generate_col_titles(*args: int) -> list[str]:
         """Generate column titles for tableau of specific dimensions
 
-        >>> Tableau.generate_col_titles(2, 3, 1)
+        >>> Tableau(np.array([[-1,-1,0,0,1],[1,3,1,0,4],[3,1,0,1,4.]]),
-        ['x1', 'x2', 's1', 's2', 's3', 'a1', 'RHS']
+        ... 2, 0).generate_col_titles()
+        ['x1', 'x2', 's1', 's2', 'RHS']
 
-        >>> Tableau.generate_col_titles()
+        >>> Tableau(np.array([[-1,-1,0,0,1],[1,3,1,0,4],[3,1,0,1,4.]]),
-        Traceback (most recent call last):
+        ... 2, 2).generate_col_titles()
-        ...
+        ['x1', 'x2', 'RHS']
-        ValueError: Must provide n_vars, n_slack, and n_art_vars
-        >>> Tableau.generate_col_titles(-2, 3, 1)
-        Traceback (most recent call last):
-        ...
-        ValueError: All arguments must be non-negative integers
         """
-        if len(args) != 3:
+        args = (self.n_vars, self.n_slack)
-            raise ValueError("Must provide n_vars, n_slack, and n_art_vars")
 
-        if not all(x >= 0 and isinstance(x, int) for x in args):
+        # decision | slack
-            raise ValueError("All arguments must be non-negative integers")
+        string_starts = ["x", "s"]
-
-        # decision | slack | artificial
-        string_starts = ["x", "s", "a"]
         titles = []
-        for i in range(3):
+        for i in range(2):
             for j in range(args[i]):
                 titles.append(string_starts[i] + str(j + 1))
         titles.append("RHS")
         return titles
 
-    def find_pivot(self, tableau: np.ndarray) -> tuple[Any, Any]:
+    def find_pivot(self) -> tuple[Any, Any]:
         """Finds the pivot row and column.
-        >>> t = Tableau(np.array([[-2,1,0,0,0], [3,1,1,0,6], [1,2,0,1,7.]]), 2)
+        >>> Tableau(np.array([[-2,1,0,0,0], [3,1,1,0,6], [1,2,0,1,7.]]),
-        >>> t.find_pivot(t.tableau)
+        ... 2, 0).find_pivot()
         (1, 0)
         """
         objective = self.objectives[-1]
 
         # Find entries of highest magnitude in objective rows
         sign = (objective == "min") - (objective == "max")
-        col_idx = np.argmax(sign * tableau[0, : self.n_vars])
+        col_idx = np.argmax(sign * self.tableau[0, :-1])
 
         # Choice is only valid if below 0 for maximise, and above for minimise
         if sign * self.tableau[0, col_idx] <= 0:
@@ -117,15 +128,15 @@ class Tableau:
         s = slice(self.n_stages, self.n_rows)
 
         # RHS
-        dividend = tableau[s, -1]
+        dividend = self.tableau[s, -1]
 
         # Elements of pivot column within slice
-        divisor = tableau[s, col_idx]
+        divisor = self.tableau[s, col_idx]
 
         # Array filled with nans
         nans = np.full(self.n_rows - self.n_stages, np.nan)
 
-        # If element in pivot column is greater than zeron_stages, return
+        # If element in pivot column is greater than zero, return
         # quotient or nan otherwise
         quotients = np.divide(dividend, divisor, out=nans, where=divisor > 0)
 
@@ -134,18 +145,18 @@ class Tableau:
         row_idx = np.nanargmin(quotients) + self.n_stages
         return row_idx, col_idx
 
-    def pivot(self, tableau: np.ndarray, row_idx: int, col_idx: int) -> np.ndarray:
+    def pivot(self, row_idx: int, col_idx: int) -> np.ndarray:
         """Pivots on value on the intersection of pivot row and column.
 
-        >>> t = Tableau(np.array([[-2,-3,0,0,0],[1,3,1,0,4],[3,1,0,1,4.]]), 2)
+        >>> Tableau(np.array([[-2,-3,0,0,0],[1,3,1,0,4],[3,1,0,1,4.]]),
-        >>> t.pivot(t.tableau, 1, 0).tolist()
+        ... 2, 2).pivot(1, 0).tolist()
         ... # doctest: +NORMALIZE_WHITESPACE
         [[0.0, 3.0, 2.0, 0.0, 8.0],
         [1.0, 3.0, 1.0, 0.0, 4.0],
         [0.0, -8.0, -3.0, 1.0, -8.0]]
         """
         # Avoid changes to original tableau
-        piv_row = tableau[row_idx].copy()
+        piv_row = self.tableau[row_idx].copy()
 
         piv_val = piv_row[col_idx]
 
@@ -153,48 +164,47 @@ class Tableau:
         piv_row *= 1 / piv_val
 
         # Variable in pivot column becomes basic, ie the only non-zero entry
-        for idx, coeff in enumerate(tableau[:, col_idx]):
+        for idx, coeff in enumerate(self.tableau[:, col_idx]):
-            tableau[idx] += -coeff * piv_row
+            self.tableau[idx] += -coeff * piv_row
-        tableau[row_idx] = piv_row
+        self.tableau[row_idx] = piv_row
-        return tableau
+        return self.tableau
 
-    def change_stage(self, tableau: np.ndarray) -> np.ndarray:
+    def change_stage(self) -> np.ndarray:
         """Exits first phase of the two-stage method by deleting artificial
         rows and columns, or completes the algorithm if exiting the standard
         case.
 
-        >>> t = Tableau(np.array([
+        >>> Tableau(np.array([
         ... [3, 3, -1, -1, 0, 0, 4],
         ... [2, 1, 0, 0, 0, 0, 0.],
         ... [1, 2, -1, 0, 1, 0, 2],
         ... [2, 1, 0, -1, 0, 1, 2]
-        ... ]), 2)
+        ... ]), 2, 2).change_stage().tolist()
-        >>> t.change_stage(t.tableau).tolist()
         ... # doctest: +NORMALIZE_WHITESPACE
-        [[2.0, 1.0, 0.0, 0.0, 0.0, 0.0],
+        [[2.0, 1.0, 0.0, 0.0, 0.0],
-        [1.0, 2.0, -1.0, 0.0, 1.0, 2.0],
+        [1.0, 2.0, -1.0, 0.0, 2.0],
-        [2.0, 1.0, 0.0, -1.0, 0.0, 2.0]]
+        [2.0, 1.0, 0.0, -1.0, 2.0]]
         """
         # Objective of original objective row remains
         self.objectives.pop()
 
         if not self.objectives:
-            return tableau
+            return self.tableau
 
         # Slice containing ids for artificial columns
-        s = slice(-self.n_art_vars - 1, -1)
+        s = slice(-self.n_artificial_vars - 1, -1)
 
         # Delete the artificial variable columns
-        tableau = np.delete(tableau, s, axis=1)
+        self.tableau = np.delete(self.tableau, s, axis=1)
 
         # Delete the objective row of the first stage
-        tableau = np.delete(tableau, 0, axis=0)
+        self.tableau = np.delete(self.tableau, 0, axis=0)
 
         self.n_stages = 1
         self.n_rows -= 1
-        self.n_art_vars = 0
+        self.n_artificial_vars = 0
         self.stop_iter = False
-        return tableau
+        return self.tableau
 
     def run_simplex(self) -> dict[Any, Any]:
         """Operate on tableau until objective function cannot be
@@ -205,15 +215,29 @@ class Tableau:
         ST:   x1 + 3x2 <= 4
              3x1 +  x2 <= 4
         >>> Tableau(np.array([[-1,-1,0,0,0],[1,3,1,0,4],[3,1,0,1,4.]]),
-        ... 2).run_simplex()
+        ... 2, 0).run_simplex()
         {'P': 2.0, 'x1': 1.0, 'x2': 1.0}
 
+        # Standard linear program with 3 variables:
+        Max: 3x1 +  x2 + 3x3
+        ST:  2x1 +  x2 +  x3 ≤ 2
+              x1 + 2x2 + 3x3 ≤ 5
+             2x1 + 2x2 +  x3 ≤ 6
+        >>> Tableau(np.array([
+        ... [-3,-1,-3,0,0,0,0],
+        ... [2,1,1,1,0,0,2],
+        ... [1,2,3,0,1,0,5],
+        ... [2,2,1,0,0,1,6.]
+        ... ]),3,0).run_simplex() # doctest: +ELLIPSIS
+        {'P': 5.4, 'x1': 0.199..., 'x3': 1.6}
+
+
         # Optimal tableau input:
         >>> Tableau(np.array([
         ... [0, 0, 0.25, 0.25, 2],
         ... [0, 1, 0.375, -0.125, 1],
         ... [1, 0, -0.125, 0.375, 1]
-        ... ]), 2).run_simplex()
+        ... ]), 2, 0).run_simplex()
         {'P': 2.0, 'x1': 1.0, 'x2': 1.0}
 
         # Non-standard: >= constraints
@@ -227,7 +251,7 @@ class Tableau:
         ... [1, 1, 1, 1, 0, 0, 0, 0, 40],
         ... [2, 1, -1, 0, -1, 0, 1, 0, 10],
         ... [0, -1, 1, 0, 0, -1, 0, 1, 10.]
-        ... ]), 3).run_simplex()
+        ... ]), 3, 2).run_simplex()
         {'P': 70.0, 'x1': 10.0, 'x2': 10.0, 'x3': 20.0}
 
         # Non standard: minimisation and equalities
@@ -235,73 +259,76 @@ class Tableau:
         ST: 2x1 +  x2 = 12
             6x1 + 5x2 = 40
         >>> Tableau(np.array([
-        ... [8, 6, 0, -1, 0, -1, 0, 0, 52],
+        ... [8, 6, 0, 0, 52],
-        ... [1, 1, 0, 0, 0, 0, 0, 0, 0],
+        ... [1, 1, 0, 0, 0],
-        ... [2, 1, 1, 0, 0, 0, 0, 0, 12],
+        ... [2, 1, 1, 0, 12],
-        ... [2, 1, 0, -1, 0, 0, 1, 0, 12],
+        ... [6, 5, 0, 1, 40.],
-        ... [6, 5, 0, 0, 1, 0, 0, 0, 40],
+        ... ]), 2, 2).run_simplex()
-        ... [6, 5, 0, 0, 0, -1, 0, 1, 40.]
-        ... ]), 2).run_simplex()
         {'P': 7.0, 'x1': 5.0, 'x2': 2.0}
+
+
+        # Pivot on slack variables
+        Max: 8x1 + 6x2
+        ST:   x1 + 3x2 <= 33
+             4x1 + 2x2 <= 48
+             2x1 + 4x2 <= 48
+              x1 +  x2 >= 10
+             x1        >= 2
+        >>> Tableau(np.array([
+        ... [2, 1, 0, 0, 0, -1, -1, 0, 0, 12.0],
+        ... [-8, -6, 0, 0, 0, 0, 0, 0, 0, 0.0],
+        ... [1, 3, 1, 0, 0, 0, 0, 0, 0, 33.0],
+        ... [4, 2, 0, 1, 0, 0, 0, 0, 0, 60.0],
+        ... [2, 4, 0, 0, 1, 0, 0, 0, 0, 48.0],
+        ... [1, 1, 0, 0, 0, -1, 0, 1, 0, 10.0],
+        ... [1, 0, 0, 0, 0, 0, -1, 0, 1, 2.0]
+        ... ]), 2, 2).run_simplex() # doctest: +ELLIPSIS
+        {'P': 132.0, 'x1': 12.000... 'x2': 5.999...}
         """
         # Stop simplex algorithm from cycling.
-        for _ in range(100):
+        for _ in range(Tableau.maxiter):
             # Completion of each stage removes an objective. If both stages
             # are complete, then no objectives are left
             if not self.objectives:
-                self.col_titles = self.generate_col_titles(
-                    self.n_vars, self.n_slack, self.n_art_vars
-                )
-
                 # Find the values of each variable at optimal solution
-                return self.interpret_tableau(self.tableau, self.col_titles)
+                return self.interpret_tableau()
 
-            row_idx, col_idx = self.find_pivot(self.tableau)
+            row_idx, col_idx = self.find_pivot()
 
             # If there are no more negative values in objective row
             if self.stop_iter:
                 # Delete artificial variable columns and rows. Update attributes
-                self.tableau = self.change_stage(self.tableau)
+                self.tableau = self.change_stage()
             else:
-                self.tableau = self.pivot(self.tableau, row_idx, col_idx)
+                self.tableau = self.pivot(row_idx, col_idx)
         return {}
 
-    def interpret_tableau(
+    def interpret_tableau(self) -> dict[str, float]:
-        self, tableau: np.ndarray, col_titles: list[str]
-    ) -> dict[str, float]:
         """Given the final tableau, add the corresponding values of the basic
         decision variables to the `output_dict`
-        >>> tableau = np.array([
+        >>> Tableau(np.array([
         ... [0,0,0.875,0.375,5],
         ... [0,1,0.375,-0.125,1],
         ... [1,0,-0.125,0.375,1]
-        ... ])
+        ... ]),2, 0).interpret_tableau()
-        >>> t = Tableau(tableau, 2)
-        >>> t.interpret_tableau(tableau, ["x1", "x2", "s1", "s2", "RHS"])
         {'P': 5.0, 'x1': 1.0, 'x2': 1.0}
         """
         # P = RHS of final tableau
-        output_dict = {"P": abs(tableau[0, -1])}
+        output_dict = {"P": abs(self.tableau[0, -1])}
 
         for i in range(self.n_vars):
-            # Gives ids of nonzero entries in the ith column
+            # Gives indices of nonzero entries in the ith column
-            nonzero = np.nonzero(tableau[:, i])
+            nonzero = np.nonzero(self.tableau[:, i])
             n_nonzero = len(nonzero[0])
 
-            # First entry in the nonzero ids
+            # First entry in the nonzero indices
             nonzero_rowidx = nonzero[0][0]
-            nonzero_val = tableau[nonzero_rowidx, i]
+            nonzero_val = self.tableau[nonzero_rowidx, i]
 
             # If there is only one nonzero value in column, which is one
-            if n_nonzero == nonzero_val == 1:
+            if n_nonzero == 1 and nonzero_val == 1:
-                rhs_val = tableau[nonzero_rowidx, -1]
+                rhs_val = self.tableau[nonzero_rowidx, -1]
-                output_dict[col_titles[i]] = rhs_val
+                output_dict[self.col_titles[i]] = rhs_val
-
-        # Check for basic variables
-        for title in col_titles:
-            # Don't add RHS or slack variables to output dict
-            if title[0] not in "R-s-a":
-                output_dict.setdefault(title, 0)
         return output_dict
 
 

machine_learning/k_means_clust.py

@@ -10,11 +10,11 @@ Inputs:
   - k , number of clusters to create.
   - initial_centroids , initial centroid values generated by utility function(mentioned
     in usage).
-  - maxiter , maximum number of iterations to process.
+  - maxiter , the maximum number of iterations to process.
-  - heterogeneity , empty list that will be filled with hetrogeneity values if passed
+  - heterogeneity, empty list that will be filled with heterogeneity values if passed
     to kmeans func.
 Usage:
-  1. define 'k' value, 'X' features array and 'hetrogeneity' empty list
+  1. define 'k' value, 'X' features array and 'heterogeneity' empty list
   2. create initial_centroids,
         initial_centroids = get_initial_centroids(
             X,
@@ -31,8 +31,8 @@ Usage:
             record_heterogeneity=heterogeneity,
             verbose=True # whether to print logs in console or not.(default=False)
             )
-  4. Plot the loss function, hetrogeneity values for every iteration saved in
+  4. Plot the loss function, heterogeneity values for every iteration saved in
-     hetrogeneity list.
+     heterogeneity list.
         plot_heterogeneity(
             heterogeneity,
             k
@@ -47,6 +47,7 @@ import pandas as pd
 from matplotlib import pyplot as plt
 from sklearn.metrics import pairwise_distances
 
+
 warnings.filterwarnings("ignore")
 
 TAG = "K-MEANS-CLUST/ "
@@ -131,7 +132,7 @@ def kmeans(
     """This function runs k-means on given data and initial set of centroids.
     maxiter: maximum number of iterations to run.(default=500)
     record_heterogeneity: (optional) a list, to store the history of heterogeneity
-                          as function of iterations
+                          as function of iterations.
                           if None, do not store the history.
     verbose: if True, print how many data points changed their cluster labels in
                           each iteration"""
@@ -198,10 +199,10 @@ def report_generator(
     df: pd.DataFrame, clustering_variables: np.ndarray, fill_missing_report=None
 ) -> pd.DataFrame:
     """
-    Function generates easy-erading clustering report. It takes 2 arguments as an input:
+    Function generates an easy-reading clustering report. It takes 3 arguments as input:
-        DataFrame - dataframe with predicted cluester column;
+        DataFrame,predicted cluster column,
-        FillMissingReport - dictionary of rules how we are going to fill missing
+        FillMissingReport - dictionary of rules on how we are going to fill in missing
-        values of for final report generate (not included in modeling);
+        values of for final report generate (not included in modelling);
     in order to run the function following libraries must be imported:
         import pandas as pd
         import numpy as np
@@ -306,10 +307,10 @@ def report_generator(
     a.columns = report.columns  # rename columns to match report
     report = report.drop(
         report[report.Type == "count"].index
-    )  # drop count values except cluster size
+    )  # drop count values except for cluster size
     report = pd.concat(
-        [report, a, clustersize, clusterproportion], axis=0
+        [report, a, cluster size, clusterproportion], axis=0
-    )  # concat report with clustert size and nan values
+    )  # concat report with cluster size and nan values
     report["Mark"] = report["Features"].isin(clustering_variables)
     cols = report.columns.tolist()
     cols = cols[0:2] + cols[-1:] + cols[2:-1]

sorts/bucket_sort.py

@@ -30,7 +30,7 @@ Source: https://en.wikipedia.org/wiki/Bucket_sort
 from __future__ import annotations
 
 
-def bucket_sort(my_list: list) -> list:
+def bucket_sort(my_list: list, bucket_count: int = 10) -> list:
     """
     >>> data = [-1, 2, -5, 0]
     >>> bucket_sort(data) == sorted(data)
@@ -43,21 +43,27 @@ def bucket_sort(my_list: list) -> list:
     True
     >>> bucket_sort([]) == sorted([])
     True
+    >>> data = [-1e10, 1e10]
+    >>> bucket_sort(data) == sorted(data)
+    True
     >>> import random
     >>> collection = random.sample(range(-50, 50), 50)
     >>> bucket_sort(collection) == sorted(collection)
     True
     """
-    if len(my_list) == 0:
+
+    if len(my_list) == 0 or bucket_count <= 0:
         return []
+
     min_value, max_value = min(my_list), max(my_list)
-    bucket_count = int(max_value - min_value) + 1
+    bucket_size = (max_value - min_value) / bucket_count
     buckets: list[list] = [[] for _ in range(bucket_count)]
 
-    for i in my_list:
+    for val in my_list:
-        buckets[int(i - min_value)].append(i)
+        index = min(int((val - min_value) / bucket_size), bucket_count - 1)
+        buckets[index].append(val)
 
-    return [v for bucket in buckets for v in sorted(bucket)]
+    return [val for bucket in buckets for val in sorted(bucket)]
 
 
 if __name__ == "__main__":

web_programming/fetch_anime_and_play.py

@@ -1,7 +1,5 @@
-from xml.dom import NotFoundErr
-
 import requests
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup, NavigableString, Tag
 from fake_useragent import UserAgent
 
 BASE_URL = "https://ww1.gogoanime2.org"
@@ -41,25 +39,23 @@ def search_scraper(anime_name: str) -> list:
 
     # get list of anime
     anime_ul = soup.find("ul", {"class": "items"})
+    if anime_ul is None or isinstance(anime_ul, NavigableString):
+        msg = f"Could not find and anime with name {anime_name}"
+        raise ValueError(msg)
     anime_li = anime_ul.children
 
     # for each anime, insert to list. the name and url.
     anime_list = []
     for anime in anime_li:
-        if not isinstance(anime, NavigableString):
+        if isinstance(anime, Tag):
-            try:
+            anime_url = anime.find("a")
-                anime_url, anime_title = (
+            if anime_url is None or isinstance(anime_url, NavigableString):
-                    anime.find("a")["href"],
+                continue
-                    anime.find("a")["title"],
+            anime_title = anime.find("a")
-                )
+            if anime_title is None or isinstance(anime_title, NavigableString):
-                anime_list.append(
+                continue
-                    {
+
-                        "title": anime_title,
+            anime_list.append({"title": anime_title["title"], "url": anime_url["href"]})
-                        "url": anime_url,
-                    }
-                )
-            except (NotFoundErr, KeyError):
-                pass
 
     return anime_list
 
@@ -93,22 +89,24 @@ def search_anime_episode_list(episode_endpoint: str) -> list:
 
     # With this id. get the episode list.
     episode_page_ul = soup.find("ul", {"id": "episode_related"})
+    if episode_page_ul is None or isinstance(episode_page_ul, NavigableString):
+        msg = f"Could not find any anime eposiodes with name {anime_name}"
+        raise ValueError(msg)
     episode_page_li = episode_page_ul.children
 
     episode_list = []
     for episode in episode_page_li:
-        try:
+        if isinstance(episode, Tag):
-            if not isinstance(episode, NavigableString):
+            url = episode.find("a")
-                episode_list.append(
+            if url is None or isinstance(url, NavigableString):
-                    {
+                continue
-                        "title": episode.find("div", {"class": "name"}).text.replace(
+            title = episode.find("div", {"class": "name"})
-                            " ", ""
+            if title is None or isinstance(title, NavigableString):
-                        ),
+                continue
-                        "url": episode.find("a")["href"],
+
-                    }
+            episode_list.append(
-                )
+                {"title": title.text.replace(" ", ""), "url": url["href"]}
-        except (KeyError, NotFoundErr):
+            )
-            pass
 
     return episode_list
 
@@ -140,11 +138,16 @@ def get_anime_episode(episode_endpoint: str) -> list:
 
     soup = BeautifulSoup(response.text, "html.parser")
 
-    try:
+    url = soup.find("iframe", {"id": "playerframe"})
-        episode_url = soup.find("iframe", {"id": "playerframe"})["src"]
+    if url is None or isinstance(url, NavigableString):
-        download_url = episode_url.replace("/embed/", "/playlist/") + ".m3u8"
+        msg = f"Could not find url and download url from {episode_endpoint}"
-    except (KeyError, NotFoundErr) as e:
+        raise RuntimeError(msg)
-        raise e
+
+    episode_url = url["src"]
+    if not isinstance(episode_url, str):
+        msg = f"Could not find url and download url from {episode_endpoint}"
+        raise RuntimeError(msg)
+    download_url = episode_url.replace("/embed/", "/playlist/") + ".m3u8"
 
     return [f"{BASE_URL}{episode_url}", f"{BASE_URL}{download_url}"]
 

web_programming/get_top_billionaires.py

@@ -3,7 +3,7 @@ CAUTION: You may get a json.decoding error.
 This works for some of us but fails for others.
 """
 
-from datetime import datetime
+from datetime import UTC, datetime, timedelta
 
 import requests
 from rich import box
@@ -20,18 +20,31 @@ API_URL = (
 )
 
 
-def calculate_age(unix_date: int) -> str:
+def calculate_age(unix_date: float) -> str:
     """Calculates age from given unix time format.
 
     Returns:
         Age as string
 
-    >>> calculate_age(-657244800000)
+    >>> from datetime import datetime, UTC
-    '73'
+    >>> years_since_create = datetime.now(tz=UTC).year - 2022
-    >>> calculate_age(46915200000)
+    >>> int(calculate_age(-657244800000)) - years_since_create
-    '51'
+    73
+    >>> int(calculate_age(46915200000)) - years_since_create
+    51
     """
-    birthdate = datetime.fromtimestamp(unix_date / 1000).date()
+    # Convert date from milliseconds to seconds
+    unix_date /= 1000
+
+    if unix_date < 0:
+        # Handle timestamp before epoch
+        epoch = datetime.fromtimestamp(0, tz=UTC)
+        seconds_since_epoch = (datetime.now(tz=UTC) - epoch).seconds
+        birthdate = (
+            epoch - timedelta(seconds=abs(unix_date) - seconds_since_epoch)
+        ).date()
+    else:
+        birthdate = datetime.fromtimestamp(unix_date, tz=UTC).date()
     return str(
         TODAY.year
         - birthdate.year