import matplotlib.pyplot as plt
'''
x1 = [1, 2, 3]
y1 = [10, 5, 7]
y2 = [4,8,3,7,5 ]
x2= [1, 2, 3, 4, 5]
x3 = [2, 4, 5, 6, 7]
y3 = [1,5,6,9, 8]
plt.title("First diagram")
plt.xlabel("X axis")
plt.ylabel("Y axis")
#plt.xlim(1,8)
plt.ylim(1, 10)
#plt.plot(x1, y1, label="Line 1", color="red", linestyle="dashed", linewidth=3, marker="o", markerfacecolor="blue", markersize=20)
#plt.plot(x2, y2, label="Line 2")
#plt.scatter(x3, y3, label="Random points")
#plt.scatter(x1, y1, label="Random points 2")
labels = ["Apples", "Bannanas", "Oranges"]
#plt.pie(y1, labels=labels, explode = (0.1,0.2,0.4))
#plt.legend()
ages = [20, 35, 35, 98, 31, 23, 23, 76, 45, 12, 10, 30, 24, 57, 90, 78, 51, 34, 47]
plt.hist(ages, 10)
plt.show()
'''

def preprocess_data(file):
  parsed_data = []
  for line in file.readlines():
    parsed_line = {}
    parts = line.split(",")
    parsed_line["publication_date"] = parts[0]
    parsed_line["title"] = ",".join(parts[1:])
    parsed_data.append(parsed_line)
  return parsed_data


processed_data = []
with open("./examiner-date-text.csv", "r") as data:
  processed_data = preprocess_data(data)
  
date_counts = {}
for item in processed_data[1:]:
  if item["publication_date"] in date_counts.keys():
    date_counts[item["publication_date"]] += 1
  else:
    date_counts[item["publication_date"]] = 1

sorted_date_counts = sorted(date_counts.items(), key=lambda item: item[0])

frequencies = list(map(lambda item: item[1], sorted_date_counts))
print(frequencies)
plt.hist(frequencies, 20)
plt.xlabel("time")
plt.ylabel("number of articles")
plt.show()
#day_count = len(date_counts.keys())
#articles_count = len(processed_data)
#average_article_count = articles_count / day_count
'''for date in date_counts.keys():
  print(date + ": " + str(date_counts[date]) + " articles")
print(average_article_count)



word_counts = {}
for item in processed_data[1:]:
  words = item["title"].split(" ")
  for word in words:
    if word.lower() in word_counts.keys():
      word_counts[word.lower()] += 1
    else:
      word_counts[word.lower()] = 1

sorted_counts = sorted(word_counts.items(), key=lambda item: item[1], reverse=True)
for i in range(100):
  print(str(sorted_counts[i][0]) + " freq: " + str(sorted_counts[i][1]))'''