?p=3014

前言

預測是通過基於來自過去和當前狀態的信息來對將要發生的事情做出聲明。

每個人每天都以不同程度的成功解決預測問題。例如，需要預測天氣，收獲，能源消耗，外匯（外匯）貨幣對或股票，地震和許多其他東西的變動。...

預測分析

通過分類，深度學習能夠在例如圖像中的像素和人的名稱之間建立相關性。你可以稱之為靜態預測。出於同樣的原因，暴露於足夠的正確數據，深度學習能夠建立當前事件和未來事件之間的相關性。從某種意義上說，未來的事件就像標簽一樣。深度學習並不一定關心時間，或者事情尚未發生。給定時間序列，深度學習可以讀取一串數字並預測下一個最可能發生的數字。

數據樣例：

2011001;3;9;20;24;26;32;10
2011002;6;8;12;17;28;33;5
2011003;13;14;21;22;23;27;4
2011004;4;6;8;10;13;26;5
2011005;6;9;12;14;20;22;13
2011006;1;3;5;13;16;18;5
2011007;1;9;17;24;26;31;5
2011008;10;12;13;17;24;31;15
2011009;17;18;23;24;25;26;4
2011010;1;4;5;9;15;19;13
2011011;1;12;18;19;21;24;10
2011012;7;8;11;13;15;26;13
2011013;1;3;13;16;21;22;8
2011014;5;7;10;11;23;26;1

截屏

import random
for x in range(0,6):#NUM_OF_RED=6
    choice_num_red = random.choice( redBalls )
    print( choice_num_red )
    redBalls.remove(choice_num_red)
for y in range(0,1):#NUM_OF_BLUE=1
    choice_num_blue = random.choice( blueBalls )
    print( choice_num_blue )
#scipy test code

#matplotlib test 
print(pylab.plot(abs(b)))
#show()
#from matplotlib.mlab import normpdf
#import matplotlib.numerix as nx
#import pylab as p
#
#x = nx.arange(-4, 4, 0.01)
#y = normpdf(x, 0, 1) # unit normal
#p.plot(x,y, color='red', lw=2)
#p.show()


plt.plot(dfs_blue_balls_count_values,'x',label='Dot plot')
plt.legend()
plt.ylabel('Y-axis,number of blue balls')
plt.xlabel('X-axis,number of duplication')
plt.show()
#Jitter plot
idx_min = min(dfs_blue_balls_count_values)
idx_max = max(dfs_blue_balls_count_values)
idx_len = idx_max-idx_min
print("min:",idx_min,"max:",idx_max)
num_jitter = 0
samplers = random.sample(range(idx_min,idx_max),idx_len)
while num_jitter < 5:
    samplers += random.sample(range(idx_min,idx_max),idx_len)
    num_jitter += 1
##lots of jitter effect
print("samplers:",samplers)
#plt.plot(samplers,'ro',label='Jitter plot')
#plt.ylabel('Y-axis,number of blue balls')
#plt.xlabel('X-axis,number of duplication')
#plt.legend()
#plt.show()
#Histograms and Kernel Density Estimates:
#Scott rule,
#This rule assumes that the data follows a Gaussian distribution;

#Plotting the blue balls appear frequency histograms(x-axis:frequency,y-axis:VIPs)
##@see http://pandas.pydata.org/pandas-docs/dev/basics.html#value-counts-histogramming
num_of_bin = len(series_blue_balls_value_counts)
array_of_ball_names = series_blue_balls_value_counts.keys()
print("Blue ball names:",array_of_ball_names)
list_merged_by_ball_id = []
for x in xrange(0,num_of_bin):
    num_index = x+1.5
    list_merged_by_ball_id += [num_index]*dfs_blue_balls_count_values[x]
print("list_merged_by_ball_id:",list_merged_by_ball_id)  
##Histograms plotting
plt.hist(list_merged_by_ball_id, bins=num_of_bin)
plt.legend()
plt.xlabel('Histograms,number of appear time by blue ball number')
plt.ylabel('Histograms,counter of appear time by blue ball number')
plt.show()
###Gaussian_KDE

##CDF(The Cumulative Distribution Function
from scipy.stats import cumfreq
idx_max = max(dfs_blue_balls_count_values)
hi = idx_max
a = numpy.arange(hi) ** 2
#    for nbins in ( 2, 20, 100 ):
for nbins in dfs_blue_balls_count_values:    
    cf = cumfreq(a, nbins)  # bin values, lowerlimit, binsize, extrapoints
    w = hi / nbins
    x = numpy.linspace( w/2, hi - w/2, nbins )  # care
    # print x, cf
    plt.plot( x, cf[0], label=str(nbins) )

plt.legend()
plt.xlabel('CDF,number of appear time by blue ball number')
plt.ylabel('CDF,counter of appear time by blue ball number')
plt.show()

###Optional: Comparing Distributions with Probability Plots and QQ Plots
###Quantile plot of the server data. A quantile plot is a graph of the CDF with the x and y axes interchanged.
###Probability plot for the data set shown,a standard normal distribution:
###@see: http://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.probplot.html
import scipy.stats as stats
prob_measurements = numpy.random.normal(loc = 20, scale = 5, size=num_of_bin)   
stats.probplot(prob_measurements, dist="norm", plot=plt)
plt.show()