sim.py

import matplotlib.pyplot as plt
import numpy as np
from numpy import linalg
import warnings

def main():
  vec = {id : np.zeros(61068) for id in range(20)}
  id = -1
  names = []
  with open("usenet.txt", "r") as f:
    for line in f:
      if line[-2] == ':' and line[0] != ' ':
        id += 1
        names.append(line[:-2])
      elif ": " in line.strip():
        i = line.strip().index(": ")
        if i != -1:
          word = int(line.strip()[0:i])
          num = int(line.strip()[i + 2:])
          vec[id][word] += num

  data = np.ndarray((20, 20))
  for i in range(20):
    for j in range(20):
      data[i, j] = cos(vec[i], vec[j])

  makeHeatMap(data, names, "seismic")


def jac(x, y):
  return np.sum(np.minimum(x, y)) / np.sum(np.maximum(x, y))

def l2(x, y):
  return - np.linalg.norm(x - y, ord=2)
 
def cos(x, y):
  return np.dot(x, y) / np.linalg.norm(x, ord=2) / np.linalg.norm(y, ord=2)

def makeHeatMap(data, names, color):
  #to catch "falling back to Agg" warning
  with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    fig, ax = plt.subplots()

    #create the map w/ color bar legend
    heatmap = ax.pcolor(data, cmap=color)
    cbar = plt.colorbar(heatmap)

    # put the major ticks at the middle of each cell
    ax.set_xticks(np.arange(data.shape[0])+0.5, minor=False)
    ax.set_yticks(np.arange(data.shape[1])+0.5, minor=False)

    # want a more natural, table-like display
    ax.invert_yaxis()
    ax.xaxis.tick_top()

    ax.set_xticklabels(range(1, 21))
    ax.set_yticklabels(names)

    plt.tight_layout()

    plt.show()
    plt.close()

if __name__ == "__main__":
  main()