add direction tracking functionality to evolutionary algorithm, updat git ignore

.gitignore

@@ -7,3 +7,5 @@
 /data/songs_new.csv
 __pycache__
 *.code-workspace
+imgs/
+.DS_Store

my_cache_handler.py

@@ -1,3 +0,0 @@
-from spotipy.cache_handler import CacheHandler
-
-class CacheFileHandler(CacheHandler):

src/evolutionary_alrogithm.py

@@ -1,14 +1,18 @@
 import pandas as pd
 import numpy as np
+from scipy.spatial.distance import cosine
+import scikits.bootstrap as bootstrap
 import gradio as gr
 import plotly.express as px
 from plotly.graph_objects import Figure
+import matplotlib.pyplot as plt
 from copy import deepcopy
 from random import choice
 from typing import List, Set
 import itertools
 from sklearn.preprocessing import StandardScaler
 from src.spotipy_utils import SpotifyTrack, get_sp_client
+# plt.switch_backend('Agg') # NOTE: for traversal direction tracking viz
 
 # Initial data cleaning.
 SONG_DF = pd.read_csv("data/SpotifyAudioFeaturesApril2019.csv")
@@ -127,7 +131,7 @@ class Population:
         self.crossover_function = crossover_function
         self.mutation_size = mutation_size
         self.history_df = deepcopy(history_df)
-
+        self.distance_matrices = []
 
     def mutate(self, thumbs_up:List[Individual], thumbs_down:List[Individual], added_songs:List[Individual]):
         """ Method to call assigned mutation function through.
@@ -201,6 +205,35 @@ class Population:
                  },)
 
 
+    def generate_direction_tracking(self):
+        multidim_distance = np.stack(self.distance_matrices, axis=2)
+
+        # Compute distribution of cosine similarity amongst distance vectors between individuals of the same generation.
+        sibling_directional_similarity = np.zeros((multidim_distance.shape[2], multidim_distance.shape[0]*(multidim_distance.shape[0]-1)))
+        for t in range(multidim_distance.shape[2]):
+            cosine_similarities = []
+            for i in range(multidim_distance.shape[0]):
+                for j in range(multidim_distance.shape[0]):
+                    if i == j:
+                        continue
+
+                    cosine_similarity = cosine(multidim_distance[i,:,t], multidim_distance[j,:,t])
+
+                    cosine_similarities.append(cosine_similarity)
+
+            sibling_directional_similarity[t, :] = np.array(cosine_similarities)
+        num_obs = sibling_directional_similarity.shape[0]
+        # Compute bootstrapped CI
+        data_ci = [bootstrap.ci(sibling_directional_similarity[k, :]) for k in range(num_obs)]
+        means = [ci.sum() / 2 for ci in data_ci]
+        lower = [ci[0] for ci in data_ci]
+        upper = [ci[1] for ci in data_ci]
+
+        plt.plot(means, label = "Distribution of Cosine Similarity for Paternal Distance Vectors Among Siblings Over Time")
+        plt.fill_between(np.arange(num_obs), upper, lower, alpha = 0.5)
+        plt.savefig("cosine_dist_over_time.png")
+
+
     def update_population_history(self, thumbs_up:List[Individual], thumbs_down:List[Individual], added_songs:List[Individual]):
         """ Update the DF keeping track of the traversal history.
 
@@ -283,11 +316,17 @@ def simple_mutation(population: Population, thumbs_up:List[Individual], thumbs_d
     """
     liked_tracks = list(itertools.chain(*[thumbs_up, added_songs]))
     new_track_inds = set()
+    # Init population distance matrix
+    distance_matrix = np.zeros((population.size, population.size))
     for i in range(population.size):
         liked_track = choice(liked_tracks)
         mutated_track_genome = liked_track.genome + np.random.uniform(size=(population.size))*population.mutation_size
         child = get_closest_song_to_genome(population, mutated_track_genome, new_track_inds)
+        # Record distance vector for parent-child.
+        distance_matrix[i, :] = child.genome - liked_track.genome
         population.pop[i] = child
+    # Add to distance matrix tracking list.
+    population.distance_matrices.append(distance_matrix)
 
 
 def differential_mutation(population: Population, thumbs_up:List[Individual], thumbs_down:List[Individual], added_songs:List[Individual]):
@@ -300,6 +339,8 @@ def differential_mutation(population: Population, thumbs_up:List[Individual], th
         added_songs (List[Individual]): List of individuals added to the playlist.
     """
     new_track_inds = set()
+    # Init population distance matrix
+    distance_matrix = np.zeros((population.size, population.size))
     for i in range(population.size):
         if thumbs_down:
             disliked_track = choice(thumbs_down)
@@ -321,4 +362,8 @@ def differential_mutation(population: Population, thumbs_up:List[Individual], th
         gene_distances = attracting_track.genome - disliked_track.genome
         resulting_genome = seed_track.genome + gene_distances*population.mutation_size
         child = get_closest_song_to_genome(population, resulting_genome, new_track_inds)
+        # Record distance vector for parent-child.
+        distance_matrix[i, :] = child.genome - attracting_track.genome
         population.pop[i] = child
+    # Add to distance matrix tracking list.
+    population.distance_matrices.append(distance_matrix)