Python數據可視化分析(一)

關注公衆號，一起學習吧！

Python數據可視化

寫得比較粗淺，後面會對數據分析專題進行深入。

安裝環境matplotlib

個人前面也說了強烈建議使用Pycharm作爲Python初學者的首選IDE，主要還是因爲其強大的插件功能，很多環境都能一鍵安裝完成，像本文的matplotlib，numpy,requests等。 下面直接上效果圖：

繪製簡單的折絲圖

使用plot來繪製折線

import matplotlib.pyplot as plt

# 繪製折線圖
squares = [1, 4, 9, 16, 25]
# plt.plot(squares, linewidth=5)  # 指定折線粗細，
# #plt.show();
#
# #修改標籤文字和線條粗細
# plt.title("squre number", fontsize=24)
# plt.xlabel("Value", fontsize=14)
# plt.ylabel("square of value", fontsize=14)
# plt.tick_params(axis='both', labelsize=14)
# plt.show()

# 校正圖形
input_values = [1, 2, 3, 4, 5]
plt.plot(input_values, squares, linewidth=5)
plt.show()

生成的效果圖：

使用scatter繪製散點圖並設置樣式

import matplotlib.pyplot as plt

# 簡單的點
# plt.scatter(2, 4)
# plt.show()
#
# # 修改標籤文字和線條粗細
plt.title("squre number", fontsize=24)
plt.xlabel("Value", fontsize=14)
plt.ylabel("square of value", fontsize=14)

#設置刻度標記大小
plt.tick_params(axis='both', which='major', labelsize=14)

# 繪製散點
x_values = [1, 2, 3, 4, 5]
y_values = [1, 4, 9, 16, 25]
plt.scatter(x_values, y_values, s=100)
plt.show()

自動計算數據

import matplotlib.pyplot as plt

x_values = list(range(1, 1001))
y_values = [x ** 2 for x in x_values]
# y_values = [x * x for x in x_values]
# y_values = [x ^ 2 for x in x_values]

plt.scatter(x_values, y_values, s=40)

# 座標軸的取值範圍
# plt.axis(0, 1100, 0, 1100000)  # 依次是xmin xmax,ymin,ymax

plt.show()

隨機漫步

import matplotlib.pyplot as ply

from random import choice

class RandomWalk():
    def __init__(self, num_points=5000):
        self.num_points = num_points

        self.x_values = [0]
        self.y_values = [0]

    def fill_walk(self):

        # 不斷走，直到達到指定步數

        while len(self.x_values) < self.num_points:

            # 決定前進方向以及沿這個方向前進的距離

            x_direction = choice([1, -1])
            x_distance = choice([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
            x_step = x_direction * x_distance

            y_direction = choice([1, -1])
            y_distance = choice([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
            y_step = y_direction * y_distance

            # 不能原地踏步

            if x_step == 0 and y_step == 0:
                continue

            next_x = self.x_values[-1] + x_step
            next_y = self.y_values[-1] + y_step

            self.x_values.append(next_x)
            self.y_values.append(next_y)

rw = RandomWalk()
rw.fill_walk()
ply.scatter(rw.x_values, rw.y_values, s=15)
ply.show()

效果圖

使用Pygal模擬擲骰子

pygal能夠繪製的圖形可以訪問pygal介紹

環境安裝，直接在Pycharm上安裝插件。

import pygal

from random import randint

class Die():
    def __init__(self, num_sides=6):
        self.num_sides = num_sides;

    def roll(self):
        # 返回一個位於1和骰子面數之間的隨機值
        return randint(1, self.num_sides)

die = Die()
results = []

# 擲100次骰子，並將結果放在列表中。
for roll_num in range(10):
    result = die.roll()
    results.append(str(result))

print(results)

# 分析結果
frequencies = []
for value in range(1, die.num_sides + 1):
    frequency = results.count(value)
    frequencies.append(frequency)

print(frequencies)

# 對結果進行可視化
hist = pygal.Box()

hist.title = "result of rolling one D6 1000 times"
hist.x_labels = ['1', '2', '3', '4', '5', '6']
hist.x_title = "Result"
hist.y_title = "frequency of result"

hist.add('D6', frequencies)
hist.render_to_file('die_visual.svg')

使用Web API

1.1安裝requests

這個可以直接在Pycharm中安裝插件，非常方便。

1.2處理API響應

import requests

# 執行api調用並存儲響應

url = 'https://api.github.com/search/repositories?q=language:python&sort=stars'
r = requests.get(url)
print("Status code:", r.status_code)

# 將api響應存儲在一個變量中
response_dic = r.json()

# 處理結果
print(response_dic.keys())

得到結果：
Status code: 200
dict_keys(['total_count', 'incomplete_results', 'items'])

1.3處理響應字典

# 將api響應存儲在一個變量中
response_dic = r.json()

# 處理結果
print(response_dic.keys())

print("Total repositories:", response_dic['total_count'])

repo_dics = response_dic['items']
print("repositories returned:" + str(len(repo_dics)))

# 研究一個倉庫
repo_dic = repo_dics[0]
print("\nKeys:", str(len(repo_dic)))

# for key in sorted(repo_dic.keys()):
#     print(key)

print("Name:", repo_dic['name'])
print("Owner:", repo_dic['owner']['login'])
print("Starts:", repo_dic['stargazers_count'])
print("Repository:", repo_dic['html_url'])
print("Created:", repo_dic['created_at'])
print("Updated:", repo_dic['updated_at'])
print("Description:", repo_dic['description'])

得到結果：

Total repositories: 2061622
repositories returned:30

Keys: 71
Name: awesome-python
Owner: vinta
Starts: 40294
Repository: https://github.com/vinta/awesome-python
Created: 2014-06-27T21:00:06Z
Updated: 2017-10-29T00:50:49Z
Description: A curated list of awesome Python frameworks, libraries, software and resources