gistfile1.py

import csv
import math
import numpy as np
import matplotlib.pyplot as plt
from collections import defaultdict

DATA = [
    (400, 60),
    (15, 30),
    (480, 365),
    (993, 190),
    (600, 136),
    (150, 15),
    (115, 37),
    (50, 100),
    (0, 170),
    (130, 70),
    (3000, 783),
    (500, 560),
    (200, 50),
    (55, 35),
    (2200, 595),
    (1, 200),
    (900, 300),
    (1000, 356),
    (450, 155),
    (400, 250)
]

# 度数分布表
data = [x[1] for x in DATA]
table = {x:0 for x in range(max(data)/160+1)}
for d in DATA:
    x = d[1]
    table[x/160] += 1

x = 0    
for k, v in table.items():
    low, upper = k*160, (k+1)*160
    l = len(DATA)
    p = float(v)/l * 100
    x += p 
    print "%s~%s: %s, %s, %s, %s" % (low, upper, (low+upper)/2, v, p, x)


# ヒストグラム
bins = int(math.sqrt(len(DATA))+1)
print bins
plt.hist([x[1] for x in DATA], bins=bins)
plt.show()