import pandas as pd
unrate = pd.read_csv('unrate.csv')
unrate['DATE'] = pd.to_datetime(unrate['DATE']) #将DATE栏里的数据用时间的格式表示出来
print(unrate.head(12))
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
import matplotlib.pyplot as plt
plt.plot()
plt.show()
first_twelve = unrate[0:12]
plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.show()
plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.xticks(rotation = 45) #指定角度
#print help(plt.xticks)
plt.show()
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()
import matplotlib.pyplot as plt
fig = plt.figure() #指定一个默认画图的区间
ax1 = fig.add_subplot(4,3,1)
ax2 = fig.add_subplot(4,3,2)
ax3 = fig.add_subplot(4,3,6)
plt.show()
import numpy as np
fig = plt.figure(figsize=(4,5)) #表示当前画图域的长4，宽为5
ax1 = fig.add_subplot(2,1,1) #已经分别得到了ax1和ax2
ax2 = fig.add_subplot(2,1,2)
ax1.plot(np.random.randint(1,5,5), np.arange(5)) #对ax1和ax2分别进行画图操作
ax2.plot(np.arange(10)*3, np.arange(10))
plt.show()
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()
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')
plt.show()
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[:1])
FILM RT_user_norm Metacritic_user_nom \ 0 Avengers: Age of Ultron (2015) 4.3 3.55 IMDB_norm Fandango_Ratingvalue Fandango_Stars 0 3.9 4.5 5.0
import matplotlib.pyplot as plt
from numpy import arange
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[0, num_cols].values #表示当前这个柱的高为多少
print(bar_heights)
bar_positions = arange(5) +0.95
print(bar_positions)
fig, ax = plt.subplots()
ax.bar(bar_positions, bar_heights, 0.2) #表示当前柱形图的宽度
ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()
[4.2999999999999998 3.5499999999999998 3.8999999999999999 4.5 5.0]
[ 0.95 1.95 2.95 3.95 4.95]
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()
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()
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()
fig, ax = plt.subplots()
#ax.hist(norm_reviews['Fandango_Ratingvalue']) #默认画格
#ax.hist(norm_reviews['Fandango_Ratingvalue'], bins=20) #可以帮我们划分二十个格
ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(4,5),bins=20) #粗度为20
plt.show()
fig, ax = plt.subplots()
ax.boxplot(norm_reviews['RT_user_norm']) #找这一列
ax.set_xticklabels(['Rotten Tomatoes']) #设置底标
ax.set_ylim(0,5)
plt.show()
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)
plt.show()