Python可視化庫Matplotlib的使用

一。導入數據

import pandas as pd
unrate = pd.read_csv('unrate.csv')
unrate['DATE'] = pd.to_datetime(unrate['DATE'])
print(unrate.head(12))

 結果以下：
        DATE  VALUE
0  1948-01-01    3.4
1  1948-02-01    3.8
2  1948-03-01    4.0
3  1948-04-01    3.9
4  1948-05-01    3.5
5  1948-06-01    3.6
6  1948-07-01    3.6
7  1948-08-01    3.9
8  1948-09-01    3.8
9  1948-10-01    3.7
10 1948-11-01    3.8
11 1948-12-01    4.0
二。使用Matplotlib庫

import matplotlib.pyplot as plt
#%matplotlib inline
#Using the different pyplot functions, we can create, customize, and display a plot. For example, we can use 2 functions to :
plt.plot()
plt.show()

結果以下：

三。插入數據

first_twelve = unrate[0:12]
plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.show()

 

 因爲x軸過於緊湊，因此使用旋轉x軸的方法 結果以下。

plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.xticks(rotation=45)
#print help(plt.xticks)
plt.show()

四。設置x軸y軸說明

plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.xticks(rotation=90)
plt.xlabel('Month')
plt.ylabel('Unemployment Rate')
plt.title('Monthly Unemployment Trends, 1948')
plt.show()

五。子圖設置

import matplotlib.pyplot as plt
fig = plt.figure()
ax1 = fig.add_subplot(4,3,1)
ax2 = fig.add_subplot(4,3,2)
ax2 = fig.add_subplot(4,3,6)
plt.show()

 

 

 

 六。一個圖標多個曲線。

1.簡單實驗。

unrate['MONTH'] = unrate['DATE'].dt.month
unrate['MONTH'] = unrate['DATE'].dt.month
fig = plt.figure(figsize=(6,3))

plt.plot(unrate[0:12]['MONTH'], unrate[0:12]['VALUE'], c='red')
plt.plot(unrate[12:24]['MONTH'], unrate[12:24]['VALUE'], c='blue')

plt.show()

2.使用循環

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i])
   
plt.show()

3.設置標籤

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    label = str(1948 + i)
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label)
plt.legend(loc='best')
#print help(plt.legend)
plt.show()

 

 4。設置完整標籤

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    label = str(1948 + i)
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label)
plt.legend(loc='upper left')
plt.xlabel('Month, Integer')
plt.ylabel('Unemployment Rate, Percent')
plt.title('Monthly Unemployment Trends, 1948-1952')

plt.show()

 七。折線圖（某電影評分網站）

1.讀取數據

import pandas as pd
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_reviews = reviews[cols]
print(norm_reviews[:10])

  2.設置說明

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()

ax.bar(bar_positions, bar_heights, 0.5)//ax.bar繪製折線圖，bar_positions繪製離遠點的距離，0.5繪製離折線圖的寬度。
ax.set_xticks(tick_positions)
ax.set_xticklabels(num_cols, rotation=45)//橫軸的說明 旋轉45度 橫軸說明

ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()

3.旋轉x軸 y軸

import matplotlib.pyplot as plt
from numpy import arange
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']

bar_widths = norm_reviews.ix[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()
ax.barh(bar_positions, bar_widths, 0.5)

ax.set_yticks(tick_positions)
ax.set_yticklabels(num_cols)
ax.set_ylabel('Rating Source')
ax.set_xlabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()

 

八。 散點圖

1。基本散點圖

fig, ax = plt.subplots()
ax.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews['RT_user_norm'])
ax.set_xlabel('Fandango')
ax.set_ylabel('Rotten Tomatoes')
plt.show()

2.拆分散點圖

#Switching Axes
fig = plt.figure(figsize=(5,10))
ax1 = fig.add_subplot(2,1,1)
ax2 = fig.add_subplot(2,1,2)
ax1.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews['RT_user_norm'])
ax1.set_xlabel('Fandango')
ax1.set_ylabel('Rotten Tomatoes')
ax2.scatter(norm_reviews['RT_user_norm'], norm_reviews['Fandango_Ratingvalue'])
ax2.set_xlabel('Rotten Tomatoes')
ax2.set_ylabel('Fandango')
plt.show()

Ps:仍是呈現很強的相關性的，基本呈直線分佈

九。直方圖

 1.讀入數據

 

import pandas as pd
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
print(norm_reviews[:100])

 

 

   2.統計評分個數

fandango_distribution = norm_reviews['Fandango_Ratingvalue'].value_counts()//統計
fandango_distribution = fandango_distribution.sort_index()//排序

imdb_distribution = norm_reviews['IMDB_norm'].value_counts()
imdb_distribution = imdb_distribution.sort_index()

print(fandango_distribution)
print(imdb_distribution)

3.畫直方圖

fig, ax = plt.subplots()
#ax.hist(norm_reviews['Fandango_Ratingvalue'])
#ax.hist(norm_reviews['Fandango_Ratingvalue'],bins=20)
ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(4, 5),bins=20)//劃分的區間20個，只統計4-5區間的bins
plt.show()

4.不一樣的媒體評分圖

fig = plt.figure(figsize=(5,20))
ax1 = fig.add_subplot(4,1,1)
ax2 = fig.add_subplot(4,1,2)
ax3 = fig.add_subplot(4,1,3)
ax4 = fig.add_subplot(4,1,4)
ax1.hist(norm_reviews['Fandango_Ratingvalue'], bins=20, range=(0, 5))
ax1.set_title('Distribution of Fandango Ratings')
ax1.set_ylim(0, 50)

ax2.hist(norm_reviews['RT_user_norm'], 20, range=(0, 5))
ax2.set_title('Distribution of Rotten Tomatoes Ratings')
ax2.set_ylim(0, 50)

ax3.hist(norm_reviews['Metacritic_user_nom'], 20, range=(0, 5))
ax3.set_title('Distribution of Metacritic Ratings')
ax3.set_ylim(0, 50)

ax4.hist(norm_reviews['IMDB_norm'], 20, range=(0, 5))
ax4.set_title('Distribution of IMDB Ratings')
ax4.set_ylim(0, 50)

plt.show()

5.四分圖

fig, ax = plt.subplots()
ax.boxplot(norm_reviews['RT_user_norm'])
ax.set_xticklabels(['Rotten Tomatoes'])
ax.set_ylim(0, 5)
plt.show()

ps：四分圖就是1/4,2/4,3/4的點是多少，能夠看到大體的範圍

6.四家媒體四方圖

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
fig, ax = plt.subplots()
ax.boxplot(norm_reviews[num_cols].values)
ax.set_xticklabels(num_cols, rotation=90)
ax.set_ylim(0,5)//打分範圍
plt.show()