Matplotlib and seaborn
Last updated
import numpy as np, pandas as pd
from matplotlib import pylab
import matplotlib.pyplot as plt
import matplotlib as mpl
mpl.rcParams.update(mpl.rcParamsDefault) # 恢复matplotlib默认样式
import seaborn as sns
import scipy.stats as stats
import statsmodels as sm
from __future__ import division
# plt.style.use('ggplot') #使用ggplot的样式plt.plot(x=,y=, color=, marker=, linestyle=, linewidth= , markersize= )
plt.bar(x, y, align='center', alpha=0.5) #bar chartfig, ax = plt.subplots(nrow, ncol, figsize=(5, 3))
# fig: 给我一张画布; ax：画布上要有几个图
# 将ax看成object, 添加plot,legend, set_xlabel, set_ylabelx=np.linspace(0,10,50)
np.random.seed(10)
# stateful
plt.plot(x,np.sin(x)+x+np.random.randn(50))
plt.plot(x,np.sin(x)+0.5*x+np.random.randn(50))
plt.plot(x,np.sin(x)+2*x+np.random.rand(50))
plt.title("Three curves")
plt.show()
# stateless
fig, ax0=plt.subplots(nrows=1) # Create a figure and a set of subplots.if multiple plots, return an array to ax.
ax0.plot(x,np.sin(x)+x+np.random.randn(50))
ax0.plot(x,np.sin(x)+0.5*x+np.random.randn(50))
ax0.plot(x,np.sin(x)+2*x+np.random.rand(50))
ax0.set_title("Three curves")
plt.show()
## Plot multiple charts on the same figure: stateless only
fig=plt.figure() # crate a new figure
ax0=fig.add_subplot(211) # figure layout: 2x1. We will plot the first chart on [0,0]
ax0.plot(x,np.sin(x)+x+np.random.randn(50))
ax0.plot(x,np.sin(x)+0.5*x+np.random.randn(50))
ax0.plot(x,np.sin(x)+2*x+np.random.rand(50))
ax1=fig.add_subplot(212)
ax1.plot(x,np.sin(x)+x+np.random.randn(50))
ax1.plot(x,np.sin(x)+0.5*x+np.random.randn(50))
ax1.plot(x,np.sin(x)+2*x+np.random.rand(50))
plt.axhline(y=10,color='purple',linestyle='--')
plt.show()x=np.linspace(0,10,50)
np.random.seed(10)
fig,ax0=plt.subplots(nrows=1)
ax0.plot(x,np.sin(x)+x+np.random.randn(50))
ax0.plot(x,np.sin(x)+0.5*x+np.random.randn(50))
ax0.plot(x,np.sin(x)+2*x+np.random.rand(50))
ax0.set_title("Three curves",fontsize=20)
# 1. adjust gridline type: dotted-line
ax0.grid(color='gray', alpha=0.5, linestyle='dotted') # alpha to adjust grid transparency
# or hide the grid:
ax0.grid(True)
# 2. set x-axis label and y-axis label
ax0.set_xlabel('X')
ax0.set_ylabel('Randomization')
ax0.xaxis.label.set_size(20) # set xlabel size
ax0.yaxis.label.set_size(20) # set xlabel size
# # 3. adjust x-axis and y-axis data range
ax0.set_xticks(np.arange(min(x),max(x)+1,1)) #步长的ticks
plt.show() # used to suppress ## 用for loop to subplot
x=np.linspace(0,10)
np.random.seed(10)
# 生成数据
y1=np.sin(x)+x+np.random.randn(50)
y2=np.sin(x)+0.5*x+np.random.randn(50)
y3=np.sin(x)+2*x+np.random.randn(50)
df=pd.DataFrame({'serie1':y1,'serie2':y2,'serie3':y3})
fig=plt.figure()
fig.subplots_adjust(hspace=0.4)
i=1
for col in df.columns:
plt.subplot(df.shape[1],1,i)
plt.plot(df.loc[:,col])
plt.title(col,y=0.6,loc='right')
i+=1
fig.show()# Import data using Pandas. csv file is in a Google Drive
file_id='13WIX0uQaA4ROvsfVjqPUwbmyW07XMc9S'
link='https://drive.google.com/uc?export=download&id={FILE_ID}'
csv_url=link.format(FILE_ID=file_id)
df = pd.read_csv(csv_url)
df.head()
# Data preprocessing: rename columns, create age group
df.columns=['cust_id','first_name','last_name','gender','age','region','job','date_join',
'balance']
df['age_group'] = pd.cut(df['age'], bins=[15, 30, 50, float('Inf')], labels=['15-30', '30-50', 'Above 50'])
# Balance vs region: Barchart
dt_region_mean_bal=df.groupby(['region'])['balance'].mean()
dt_region_mean_bal = dt_region_mean_bal.reset_index() # reset index才能保证出来的是一个dataframe，方便画图 不然index就成了region了
dt_region_mean_bal['balance']=np.rint(dt_region_mean_bal['balance']) #round to the nearest integer
fig,ax0=plt.subplots(nrows=1)
ax0.bar(dt_region_mean_bal['region'],dt_region_mean_bal['balance'])
# adjust: xlabel, ylabel,y-axis scale; adjust background color
# add title
ax0.set_title("Balance by region",fontsize=20)
ax0.set_xlabel('Region')
ax0.set_ylabel('Average balance')
ax0.xaxis.label.set_size(20) # set xlabel size
ax0.yaxis.label.set_size(20) # set xlabel size
ax0.set_ylim(top=70000)
ax0.grid(False)
# what about data label?
def autolabel(rects):
"""
Attach a text label above each bar displaying its height
"""
for rect in rects:
height = rect.get_height()
ax0.text(rect.get_x() + rect.get_width()/2., 1.05*height,
'%d' % int(height),
ha='center', va='bottom')
rect1=ax0.bar(dt_region_mean_bal['region'],dt_region_mean_bal['balance'],color='blue')
autolabel(rect1)
plt.show()# use OOP + pandas plot
fig,ax1=plt.subplots(nrows=1)
df.groupby(['region','gender'])['balance'].mean().unstack().plot(kind='bar',ax=ax1)
ax1.set_ylim(top=70000)
ax1.set_title("Balance by region and gender")
ax1.set_ylabel('Average Balance')
ax1.grid(False)
plt.show()# two y-axies: example, plot conversions and conversion rate on the same chart.
ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
ts = ts.cumsum()
df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index, columns=list('ABCD'))
df = df.cumsum()
df.plot(secondary_y=['A', 'B'], mark_right=False)
plt.show()import seaborn as sns
sns.set_style('whitegrid')
#stateful
sns.boxplot(x='species', y='sepal_length', data=df_iris)
plt.xticks(rotation=-45) # adjust xticks
plt.title('Aris species sepal_length boxplox') # add title
plt.show()# boxplot UK bank client balance by age group, using seaborn and matplotlib
# stateless(OOP)
fig,ax2=plt.subplots(nrows=1)
sns.boxplot(x='age_group',y='balance',data=df,ax=ax2) # connect sns and matplotlib
ax2.grid(False)
ax2.set_title("Balance boxplot sliced by age_group")
plt.show()# Balance distribution by difference groups
# stateless(OOP)
fig = plt.figure()
ax3 = fig.add_subplot(1,1,1)
sns.distplot(df.loc[df['age_group']=='15-30','balance'],label='15-30', hist=False,ax=ax3)
sns.distplot(df.loc[df['age_group']=='30-50','balance'],label='30-50', hist=False,ax=ax3)
sns.distplot(df.loc[df['age_group']=='Above 50','balance'],label='Above 50', hist=False,ax=ax3)
ax3.grid(False)
ax3.set_title("Balance distribution by age_group")
ax3.legend()
plt.show()# barplot
df_titanic=sns.load_dataset('titanic')
g=sns.barplot(x="sex", y="survived", hue="class", ci=None, data=df_titanic)
g.set_ylabel('survival rate')
vals=g.get_yticks()
g.set_yticklabels(['{:3.2f}%'.format(x*100) for x in vals]) # if you want to show percentage for yticklabels
plt.show()# Scatterplot
sns.pairplot(data=df_iris, hue="species")
plt.show()# multiple charts and chart overlap
# stateful
fig=plt.figure(figsize=(8,16)) # X: control width, Y: control length
plt.subplot(2,1,1) # or ax0=fig.add_subplot(2,1,1)
sns.boxplot(x='species',y='sepal_length',data=df)
plt.xticks(rotation=-45) # adjust xticks
plt.title('Aris species sepal_length boxplox') # add title
plt.subplot(2,1,2)
sns.distplot(df['sepal_length'])
plt.show()# g is a sns object
g=sns.factorplot(x='time',
y='pulse',
data=df,
hue='diet', # Color by diet
col='diet', # Separate by diet
kind='box') # Swarmplot
# Rotate x-axis labels
g.set_xticklabels(rotation=-45)# 在不同社会等级下，男性和女性在不同登陆港口下的数量对比
grid = sns.FacetGrid(data_all, col='Pclass', hue='Sex', palette='seismic', size=4)
# 'Embarked' 是 data_all （是一个 DataFrame） 中的字段
grid.map(sns.countplot, 'Embarked', alpha=.8)
# 在图表的右边会显示图例
grid.add_legend()
grid = sns.FacetGrid(data_all, row='Sex', col='Pclass',
hue='Survived', palette='seismic', size=4)
grid.map(sns.countplot, 'Embarked', alpha=0.8)
grid.add_legend()
# regression plot
# Simulate data:
x = np.linspace(1,50,num=100)
epsilon = np.random.normal(0,3,size=100)
dt_lin = pd.DataFrame({'x':x, 'y':0.2+0.2*x + epsilon})
sns.set_style('whitegrid')
sns.regplot(x='x',y='y',data=dt_lin)
plt.show()# 微调， 把图形做得更简洁, 把不喜欢的gridline去掉, 加上title
fig=plt.figure(figsize=(8,4))
ax0=fig.add_subplot(121)
sns.regplot(x='x',y='y',data=dt_lin,ax=ax0)
ax1=fig.add_subplot(122)
sns.regplot(x='x',y='y',data=dt_lin,ax=ax1)
ax1.grid(False)
ax1.set_title('Clean linear regression')
plt.show()# seaborn fit a polynomial model
x = np.linspace(1,50, num = 100)
dt_poly=pd.DataFrame({'x':x,'y':0.2+0.3*np.power(x,2)})
sns.regplot(x='x', y='y',data=dt_poly,order=2, ci=None, scatter_kws={"s": 80});
plt.show()