折線圖
import pandas as pd
unrate = pd.read_csv('unrate.csv')
unrate['DATE'] = pd.to_datetime(unrate['DATE']) #時間類型轉換
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
#%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()
first_twelve = unrate[0:12]
plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.show()
#While the y-axis looks fine, the x-axis tick labels are too close together and are unreadable
#We can rotate the x-axis tick labels by 90 degrees so they don't overlap
#We can specify degrees of rotation using a float or integer value.
plt.plot(first_twelve['DATE'], first_twelve['VALUE'])
plt.xticks(rotation=45)
#print help(plt.xticks)
plt.show()
#xlabel(): accepts a string value, which gets set as the x-axis label.
#ylabel(): accepts a string value, which is set as the y-axis label.
#title(): accepts a string value, which is set as the plot title.
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()
子圖操作
#add_subplot(first,second,index) first means number of Row,second means number of Column.
import matplotlib.pyplot as plt
fig = plt.figure()
ax1 = fig.add_subplot(3,2,1)
ax2 = fig.add_subplot(3,2,2)
ax2 = fig.add_subplot(3,2,6)
plt.show()
import numpy as np
fig = plt.figure()
#fig = plt.figure(figsize=(3, 3))
ax1 = fig.add_subplot(2,1,1)
ax2 = fig.add_subplot(2,1,2)
ax1.plot(np.random.randint(1,5,5), np.arange(5))
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]
plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i])
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')
#print help(plt.legend)
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='upper left')
plt.xlabel('Month, Integer')
plt.ylabel('Unemployment Rate, Percent')
plt.title('Monthly Unemployment Trends, 1948-1952')
plt.show()
條形圖和散點圖
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 IMDB_norm Fandango_Ratingvalue Fandango_Stars
0 Avengers: Age of Ultron (2015) 4.3 3.55 3.9 4.5 5.0
import matplotlib.pyplot as plt
from numpy import arange
#The Axes.bar() method has 2 required parameters, left and height.
#We use the left parameter to specify the x coordinates of the left sides of the bar.
#We use the height parameter to specify the height of each bar
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[0, num_cols].values
#print bar_heights
bar_positions = arange(5) + 0.75
#print bar_positions
fig, ax = plt.subplots()
ax.bar(bar_positions, bar_heights, 0.5)
plt.show()
#By default, matplotlib sets the x-axis tick labels to the integer values the bars
#spanned on the x-axis (from 0 to 6). We only need tick labels on the x-axis where the bars are positioned.
#We can use Axes.set_xticks() to change the positions of the ticks to [1, 2, 3, 4, 5]:
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()
print(tick_positions)
ax.bar(bar_positions, bar_heights, 0.5)
ax.set_xticks(tick_positions)
ax.set_xticklabels(num_cols, rotation=45)
ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()
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) #縱向
#ax.bar(bar_positions, bar_heights, 0.5) 橫向
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()
#Let's look at a plot that can help us visualize many points.
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()
#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()
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) #將橫座標分成20段
plt.show()
fig, ax = plt.subplots()
ax.boxplot(norm_reviews['RT_user_norm']) #boxplot
ax.set_xticklabels(['Rotten Tomatoes'])
ax.set_ylim(0, 5) #Limit the height of the Y-axis
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()
