pandas_matplot_seaborn

import pandas as pd
#import matplotlib
#unrate= pd.read_csv("unrate.csv")
# 把时间格式 1948/1/10 转化为 1948-01-10
#unrate["DATE"] = pd.to_datetime(unrate['DATE'])
#折线图
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import pandas as pd
from scipy import stats, integrate
import matplotlib.pyplot as plt
import matplotlib as mpl

titannic = sns.load_dataset("titanic")
tips = sns.load_dataset("tips")
iris =sns.load_dataset('iris')
'''
admission = pd.read_csv(admissions.csv")
admission_t = admission[0:12]
plt.plot(admission_t['gpa'],admission_t['gre ']) # Draw pattern
plt.xticks (rotation = 25) # x axis to change the angle of the tag name 
# add axis title 
plt.xlabel ( "Hello") 
plt.ylabel ( "World") 
# add title 
plt.title ( "Hello World") 
#plt the .Show () 


Fig plt.figure = (figsize = (3,3)) Paint # default interval 
# ax1 = fig.add_subplot (2,2,1) # 2,2 representative of the size of the matrix represents the position 
# ax2 = fig. add_subplot (2.2.2) 
# = fig.add_subplot AX4 (2,2,4) 
plt.show () 

unrate = pd.read_csv ( "admissions.csv") 
Fig plt.figure = (figsize = (10,6 )) 

Colors = [ 'Red', 'Green', "Blue", "Orange", 'Black'] 
for I in Range (. 5): 
    start_index = I * 12 is 
    end_index = (I +. 1) * 12 is 
    Subset = unrate [start_index: end_index] 
    label = STR (1958 + I) in the top right corner balloon #
    plt.plot (subset [ "gpa"] , subset [ "gre"], c = colors [i], label = label) 
position plt.legend (loc = 'best') # define splat 


plt.show () 

FIG row # column 
from numpy Import aRange 
# must first acquire height data for each column in the data acquisition abscissa 
reviews = pd.read_csv ( ". csv" ) # file object obtained the DataForm 
cols = [ 'FILM', 'RT_usr_norm ',' IMDB_norm '] 
norm_recives = Reviews [cols] # Serise 

NUM_COLS = [' Frist ', "SECOND",' THIRD ',' Four ',' Five '] 
bar_height norm_recives.ix = (0, NUM_COLS) .values # height bar graph 
bar_positions = arange (5) + 0.75 # position bar graph 

Fig, AX = plt.subplots () 
ax.bar = (bar_positions, bar_height, 0.3) # 0.3 width bar graph representative of the column into window 

#plt.Show () 
# Form Series library DATa 
#ax graphics operations 
# 
fig, AX = plt.subplots ()

ax.hist (norm_recives) 

# load file 
recive_csv = pd.read_csv ( "cleaned_loans2007.csv") 
#cols = [ 'clo1', 'col2', 'col3', 'COL4'] 
#correct_csv = recive_csv [cols] 

Fig, plt.subplots = AX () 
ax.hist (recive_csv [ 'revol_bal']) gives the column name # 
# statistical distribution range of the same value and the number represented by the bar graph out 
plt.show () 

#data visualzation 

# import Paint package 
#% matplotlib inline 
DEF sinplot (= Flip. 1): 
    X = np.linspace (0,14,100) # 100 points found in the section (0,14) 
    for I in range (l, 7): # 6 lines Videos 
        plt.plot (x, np.sin (x + i * 5) * (7-i) * flip) # calculating the height of each point, and draw on a view 
    plt.show () 
#sinplot () function call # 
#seaborn set the theme style: 
#sinplot () 
sns.set_style ( 'whitegrid')
data = np.random.normal (size = (20,6 )) # + np.arange (6) / 2 # normal probability density function 
# two-dimensional array of 20 rows and 6 columns 
Print (data.shape) 
Print (data) 
sns.boxplot (data = data) loading data # 
# plt.show () # attempt to appear 
# sns.set_style ( 'ticket') # with short line segments 
Print (Help (np.linspace)) 
#sinplot ( ) calls the function 

dd = np.linspace (0,5,100) # 100 generates a random number between 0-5 and ordering 
Print (type (dd)) 
Print (dd) 

Import numpy AS NP 
N =. 8 
Y = np.zeros (N) # initialize a np.array 8 contains zeros 
Print (Y) 
X1 = np.linspace (0, 10, N, Endpoint = True) # 8 x coordinate generating 
Print (X1) 
X2 = np.linspace (0, 10, N, Endpoint = False) 
Print (X2) 
plt.plot (X1, Y, 'O') # Videos first 

plt.plot (x2, y + 0.5, 'o') # Paint

plt.ylim ([- 0.5,. 1]) 

plt.show () 


sns.set_style () Set Style # 
sns.despine (left = True) 
with sns.axes_style ( 'darkgrid'): 
    plt.subplot (211) to # FIG sub-set style setting 
    sinplot () 
sns.set_context ( "Paper") 
plt.figure (figsize = (8,6)) 

HLS color space 

Current = sns.color_palette () 
set_palette () 
index 

# sns.set (rc = { "figure.figsize" :( 6,6)}) 
Current = sns.color_palette () 
sns.palplot (sns.color_palette ( 'HLS',. 8)) relating to color change # 

# discrete continuous 
#data = np .random.normal (size = (20,8)) + np.arange (. 8) / 2 
# sns.boxplot (data = data, Palette = sns.color_palette ( 'HLS',. 4)) # type color display data attempt 
Category # l brightness color saturation 
# sns.color_palette ( 'hls', 8 , l = 7, s = 9)


plt.plot ([0.1], [0.1], sns.xkcd_rgb [ 'Pale Red'], = LW. 3) 
plt.show () 

sns.palplot (sns.color_palette ( "Blue")) # gradient 
sns.palplot ( sns.color_palette ( "Blue_r")) # gradient from dark to the front 

sns.palplot (sns.cubechelix_palette (. 8, Start =. 5, rot = -75)) 
sns.palplot (sns.light_palette ( "Green")) # gradation 

X, Y = np.random.multivariate_normal ([0,0], [[. 1, -5], [- 5,1]], size = 300) .T 
Print (X, Y) 
PAL = sns.dark_palette ( "Red", as_cmap = True) 
# Videos volcano FIG 
sns.kdeplot (x, y, cmap = pal) # passed in the position and color 
plt.show () 
when the get data analysis univariate analysis wherein a single 
data by wherein the composition, wherein the distribution of clear understanding 


sns.set (color_codes = True) 
AA = np.random.seed (SUM (Map (the ord, "distributions"))) 
Print (type (AA)) 
Print (AA) 
X = np.random.normal (size = 100) # Gaussian data generated
#kde kernel density estimation higher bins segmentation Si Lunbu 20 aliquots distribution See Fit 
X = np.random.gamma (. 6, size = 200 is) 
# Square 
sns.distplot (x, kde = False, fit = stats. gamma) # generates square FIG 
plt.show () 

# relationship between the mean and covariance of the data features characterized by a scattergram wherein single square 
mean, cov = [0,1], [(1, .5), (as .5, 1)] 
data np.random.multivariate_normal = (Mean, CoV, 200 is) # generates two-dimensional data 
df = pd.DataFrame (data, columns = [ 'x', 'y']) # format generated DataFrame data 
# scattergram method 
sns.jointplot (x = 'x', y = 'y', data = df) # scattergram generated 
plt.show () 

Mean, CoV = [0,1], [(. 1, . .5), (5,1)] 
X, Y np.random.multivariate_normal = (Mean, CoV, 1000) plus # .T .T into tuples 
with sns.axes_style ( 'white'): # design hex type specified pattern king FIG 
    sns.jointplot (X = X, Y = Y, kind = 'hex', Color = 'K') 
PLT.show () 
small amount of data played by the scattergram data amount hex FIG.


# Twenty-two wherein four feature comparison 

IRIS = sns.load_dataset ( 'IRIS') 
# visual characteristics and display characteristics between   
sns.pairplot (IRIS) 
plt.show () 

to draw a regression line type in FIG regplot () 

Tips = sns.load_dataset ( 'Tips') 

Print (tips.head ()) 
            # indexes x and y index relationship 
# sns.regplot (x = 'total_bill', y = 'Tip', data = Tips) 

                                            # data jitter 
sns.regplot (data Tips =, X = 'size', Y = 'Tip', x_jitter = .05) 
plt.show () 



#strip FIG type 
# sns.stripplot (y = 'day' , x = 'total_bill', data = tips, = False Jitter) 

# tree of FIG type 
# sns.swarmplot (X = 'Day', Y = 'total_bill', Data = Tips) 
# cassette statistically FIG IQR interquartile range of one quarter and three quarters the distance between the bit 
#N = 1.5IQR If a value> Q3 + n or <Q1-N is referred to as outlier
#sns.boxplot(x='day',y = 'total_bill',hue = 'time',data = tips)

#梯形图
#sns.violinplot(y = 'total_bill',x ='day',hue = 'time',data = tips,split= True)
#alpha = True #透明度
#柱形图
#sns.barplot(x = 'sex',y='survived',hue="class",data = titannic)

#点图
sns.pointplot(x = 'sex',y = 'survived',hue = 'class',data = titannic,palette={'male':'g','female':'m'},markers = ['^','o'],linestyles = ['-','--'])
#sns.pointplot(x = 'sex',y = 'survived',hue= 'class',data = titannic,palette={'male':'g','female':'m'},markers = ['^','o'],linestyles = ['-','-']) # plt.hist barinstantiate a FactGrid objects#G = sns.FacetGrid (Tips, COL =' Time ', hue =' smoker ')'' 'polytype FIG.")sns.factorplot (x = 'day',
# multilayer FIG





g.map # (plt.hist, 'Tip') 
# scattergram 
# g.map (plt.scatter, 'total_bill', 'Tip', Alpha =. 7) 

# Specify drawing order: 
from PANDAS Import Categorical 
ordered_days = Tips .day.value_counts (). index 
ordered_days Categorical = ([ 'Thur', 'Tri', 'Sat', 'the Sun']) 
# ( 'assign a new sort') 
G = sns.FacetGrid (Tips, Row = 'day', row_order = ordered_days, size = 7, aspect = 4) # create a FacetGrip objects 
g.map (sns.boxplot, 'total_bill') # specifies the drawing mode and data 

plt.show () # make images appear