ãã®èšäºã§ã¯ãå€æã®çè«èšç®ãåæããŸãã ç·åœ¢ååž°é¢æ° в éããžããå€æé¢æ° (ããžã¹ãã£ãã¯å¿çé¢æ°ãšãåŒã°ããŸã)ã 次ã«ãæŠåšåº«ã䜿çšããŠã æå°€æ³ãããžã¹ãã£ãã¯ååž°ã¢ãã«ã«åŸã£ãŠãæ倱é¢æ°ãå°ãåºããŸãã ç©æµæ倱ãèšãæããã°ãããžã¹ãã£ãã¯ååž°ã¢ãã«ã§éã¿ãã¯ãã«ã®ãã©ã¡ãŒã¿ãéžæãããé¢æ°ãå®çŸ©ããŸãã .
èšäºã®æŠèŠ:
- XNUMX ã€ã®å€æ°éã®ç·åœ¢é¢ä¿ãç¹°ãè¿ããŠã¿ãŸããã
- å€é©ã®å¿ èŠæ§ãç¹å®ããŸããã ç·åœ¢ååž°é¢æ° в ããžã¹ãã£ãã¯å¿çé¢æ°
- å€æããŠåºåããŠã¿ãŸããã ããžã¹ãã£ãã¯å¿çé¢æ°
- ãã©ã¡ãŒã¿ãéžæãããšãã«æå°äºä¹æ³ããªãæªãã®ããç解ããŠã¿ãŸããã æ©èœ ç©æµæ倱
- ã䜿çšããŠãããŸã æå°€æ³ æ±ºå®ããŸã ãã©ã¡ãŒã¿éžææ©èœ :
5.1. ã±ãŒã¹ 1: æ©èœ ç©æµæ倱 ã¯ã©ã¹æå®ã®ãããªããžã§ã¯ãã®å Žå 0 О 1:
5.2. ã±ãŒã¹ 2: æ©èœ ç©æµæ倱 ã¯ã©ã¹æå®ã®ãããªããžã§ã¯ãã®å Žå -1 О +1:
ãã®èšäºã«ã¯ç°¡åãªäŸãè±å¯ã«èšèŒãããŠããããã¹ãŠã®èšç®ã¯å£é ãŸãã¯çŽã§ç°¡åã«è¡ãããšãã§ããŸãããå Žåã«ãã£ãŠã¯é»åãå¿
èŠã«ãªãå ŽåããããŸãã ã ããæºåãããŠãã ãã:)
ãã®èšäºã¯äž»ã«ãæ©æ¢°åŠç¿ã®åºç€ã«é¢ããåæã¬ãã«ã®ç¥èãæã€ããŒã¿ ãµã€ãšã³ãã£ã¹ãã察象ãšããŠããŸãã
ãã®èšäºã§ã¯ãã°ã©ããæç»ãããèšç®ãããããããã®ã³ãŒããæäŸããŸãã ãã¹ãŠã®ã³ãŒãã¯èšèªã§æžãããŠããŸã python 2.7ã 䜿çšããããŒãžã§ã³ã®ãæ°èŠæ§ãã«ã€ããŠäºåã«èª¬æããŠãããŸããããã¯ãããç¥ãããŠããã³ãŒã¹ãåè¬ããããã®æ¡ä»¶ã® XNUMX ã€ã§ãã ã€ã³ããã¯ã¹ åæ§ã«æåãªãªã³ã©ã€ã³æè²ãã©ãããã©ãŒã äžã§ Coursera, ãããŠããæ³åã®ãšããããã®ææã¯ãã®ã³ãŒã¹ã«åºã¥ããŠäœæãããŸããã
01. çŽç·äŸåæ§
ç·åœ¢äŸåæ§ãšããžã¹ãã£ãã¯ååž°ã¯ãããšã©ã®ãããªé¢ä¿ãããã®ã§ãããã?ãšãã質åãããã®ã¯éåžžã«åççã§ãã
ããã¯ç°¡åã§ãïŒ ããžã¹ãã£ãã¯ååž°ã¯ãç·åœ¢åé¡åšã«å±ããã¢ãã«ã® XNUMX ã€ã§ãã ç°¡åã«èšãã°ãç·åœ¢åé¡åšã®ã¿ã¹ã¯ã¯ã¿ãŒã²ããå€ãäºæž¬ããããšã§ãã å€æ°ãã (ãªã°ã¬ããµãŒ) ã ç¹æ§éã®äŸåé¢ä¿ããããšèããããŠããŸãã ãšç®æšå€ ç·åœ¢ã ãããã£ãŠãåé¡åšã®ååã¯ç·åœ¢ã§ãã éåžžã«å€§ãŸãã«èšããšãããžã¹ãã£ãã¯ååž°ã¢ãã«ã¯ãç¹æ§éã«ç·åœ¢é¢ä¿ããããšããä»®å®ã«åºã¥ããŠããŸãã ãšç®æšå€ ã ãããã€ãªããã§ãã
ã¹ã¿ãžãªã«æåã®äŸããããŸããããã¯ãæ£ããã¯ãç 究察象ã®éã®çŽç·äŸåæ§ã«é¢ãããã®ã§ãã èšäºãæºåããéçšã§ããã§ã«å€ãã®äººãäžå®ã«ãããŠããäŸãã€ãŸãé»æµãšé»å§ã®äŸåé¢ä¿ã«ééããŸããã (ãå¿çšååž°åæããN. ãã¬ã€ããŒãG. ã¹ãã¹)ã ããã§ãèŠãŠãããŸãã
ã«å¿ã㊠ãªãŒã ã®æ³å:
ã©ã - çŸåšã®åŒ·ãã - é»å§ã - æµæã
ç§ãã¡ãç¥ããªãã£ãã ãªãŒã ã®æ³åãå€æŽããããšã§ãçµéšçã«äŸåé¢ä¿ãèŠã€ããããšãã§ããŸãã ãããŠæž¬å® ããµããŒãããªãã ä¿®çæžã¿ã 次ã«ãäŸåã°ã©ãã次ã®ããã«ãªã£ãŠããããšãããããŸãã ãã åç¹ãéãã»ãŒçŽç·ãåŸãããŸãã ãã»ãŒããšèšã£ãã®ã¯ããã®é¢ä¿ã¯å®éã«ã¯æ£ç¢ºã§ããã枬å®å€ã«ã¯å°ããªèª€å·®ãå«ãŸããå¯èœæ§ãããããã®ããã°ã©ãäžã®ç¹ãæ£ç¢ºã«ç·äžã«åãŸããããã®åšãã«ã©ã³ãã ã«ç¹åšããå¯èœæ§ãããããã§ãã
ã°ã©ã1ãäŸåæ§ã ãã »
ãã£ãŒãæç»ã³ãŒã
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import random
R = 13.75
x_line = np.arange(0,220,1)
y_line = []
for i in x_line:
y_line.append(i/R)
y_dot = []
for i in y_line:
y_dot.append(i+random.uniform(-0.9,0.9))
fig, axes = plt.subplots(figsize = (14,6), dpi = 80)
plt.plot(x_line,y_line,color = 'purple',lw = 3, label = 'I = U/R')
plt.scatter(x_line,y_dot,color = 'red', label = 'Actual results')
plt.xlabel('I', size = 16)
plt.ylabel('U', size = 16)
plt.legend(prop = {'size': 14})
plt.show()
02. ç·åœ¢ååž°åŒãå€æããå¿ èŠæ§
å¥ã®äŸãèŠãŠã¿ãŸãããã ç§ãã¡ãéè¡ã§åããŠãããç§ãã¡ã®ä»äºã¯ãç¹å®ã®èŠå ã«å¿ããŠåãæãããŒã³ãè¿æžããå¯èœæ§ãå€æããããšã§ãããšæ³åããŠã¿ãŸãããã ã¿ã¹ã¯ãåçŽåããããã«ãåãæã®æ絊ãšæã ã®ããŒã³è¿æžé¡ã® XNUMX ã€ã®èŠçŽ ã®ã¿ãèæ ®ããŸãã
ãã®ã¿ã¹ã¯ã¯éåžžã«æ¡ä»¶ä»ãã§ããããã®äŸã䜿çšãããšããªãããã䜿çšããã ãã§ã¯ååã§ãªãã®ããããããŸãã ç·åœ¢ååž°é¢æ°ããŸãããã®é¢æ°ã§ã©ã®ãããªå€æãå®è¡ããå¿ èŠããããã調ã¹ãŸãã
äŸã«æ»ããŸãããã 絊äžãé«ããã°é«ãã»ã©ãåãæã¯æã ã®ããŒã³è¿æžã«å ãŠãããšãã§ããé¡ãå¢ããããšãç解ãããŠããŸãã åæã«ãç¹å®ã®çµŠäžç¯å²ã§ã¯ããã®é¢ä¿ã¯éåžžã«çŽç·çã«ãªããŸãã ããšãã°ã絊äžç¯å²ã 60.000 RUR ãã 200.000 RUR ã§ãããæå®ããã絊äžç¯å²ã§ã¯ãæã ã®æ¯æãé¡ãšçµŠäžé¡ã®äŸåé¢ä¿ãç·åœ¢ã§ãããšä»®å®ããŸãã æå®ãããç¯å²ã®è³éã«ã€ããŠã絊äžå¯Ÿæ¯ææ¯çã 3 ãäžåãããšã¯ã§ãããåãæã¯ãŸã 5.000 RUR ã®æºåéãæã£ãŠããªããã°ãªããªãããšãå€æãããšããŸãã ãããŠãã®å Žåã«éããåãæãéè¡ã«ããŒã³ãè¿æžãããšä»®å®ããŸãã ãã®å Žåãç·åœ¢ååž°æ¹çšåŒã¯æ¬¡ã®åœ¢åŒã«ãªããŸãã
ã©ã , , , - çµŠäž -çªç®ã®åãæã - ããŒã³ã®æ¯æ -çªç®ã®åãæã
絊äžãšããŒã³ã®æ¯æããåºå®ãã©ã¡ãŒã¿ã§æ¹çšåŒã«ä»£å ¥ãã ããŒã³ãçºè¡ãããæåŠãããã決å®ã§ããŸãã
ä»åŸã®ããšãèãããšãæå®ããããã©ã¡ãŒã¿ã䜿çšãããšã ç·åœ¢ååž°é¢æ°ã ã§äœ¿ããã ããžã¹ãã£ãã¯å¿çé¢æ° 倧ããªå€ãçæããããããããŒã³è¿æžã®ç¢ºçã決å®ããããã®èšç®ãè€éã«ãªããŸãã ãããã£ãŠãä¿æ°ãããšãã° 25.000 åã® XNUMX ã«æžããããšãææ¡ãããŠããŸãã ãã®ä¿æ°ã®å€æã«ãã£ãŠããŒã³çºè¡ã®æ±ºå®ãå€ããããšã¯ãããŸããã ãã®ç¹ã¯å°æ¥ã®ããã«èŠããŠãããŠãã ãããããããããã§ãç§ãã¡ã話ããŠããããšãããã«æ確ã«ããããã«ãXNUMX 人ã®æœåšçãªåãæã®ç¶æ³ãèããŠã¿ãŸãããã
è¡š 1 ãæœåšçãªåãæã
ããŒãã«ãçæããã³ãŒã
import pandas as pd
r = 25000.0
w_0 = -5000.0/r
w_1 = 1.0/r
w_2 = -3.0/r
data = {'The borrower':np.array(['Vasya', 'Fedya', 'Lesha']),
'Salary':np.array([120000,180000,210000]),
'Payment':np.array([3000,50000,70000])}
df = pd.DataFrame(data)
df['f(w,x)'] = w_0 + df['Salary']*w_1 + df['Payment']*w_2
decision = []
for i in df['f(w,x)']:
if i > 0:
dec = 'Approved'
decision.append(dec)
else:
dec = 'Refusal'
decision.append(dec)
df['Decision'] = decision
df[['The borrower', 'Salary', 'Payment', 'f(w,x)', 'Decision']]
è¡šã®ããŒã¿ã«ãããšã絊æ 120.000 RUR ã® Vasya ã¯ãæã 3.000 RUR ã§è¿æžã§ããããããŒã³ãåãåããããšèããŠããŸãã ããŒã³ãæ¿èªããã«ã¯ãVasya ããã®çµŠäžãæ¯æé¡ã® 5.000 åãè¶ ããã〠XNUMX RUR ãæ®ã£ãŠããå¿ èŠããããšå€æããŸããã Vasya ã¯æ¬¡ã®èŠä»¶ãæºãããŠããŸãã ã 106.000RURãæ®ã£ãŠããŸãã ã«ãããããããèšç®ãããšã ç§ãã¡ã¯ç¢ºçãäžããŸãã 25.000 åå®è¡ããŠãçµæã¯åãã§ãããŒã³ã¯æ¿èªã§ããŸããã ãã§ãã£ã¢ãããŒã³ãåãåãããšã«ãªããããªãŒã·ã£ã¯ã圌ãæãå€ããåãåã£ãŠãããšããäºå®ã«ããããããã圌ã®é£æ¬²ãæããªããã°ãªããªãã ããã
ãã®å Žåã®ã°ã©ããæããŠã¿ãŸãããã
å³è¡šïŒãåå ¥å ã®åé¡ã
ã°ã©ããæç»ããã³ãŒã
salary = np.arange(60000,240000,20000)
payment = (-w_0-w_1*salary)/w_2
fig, axes = plt.subplots(figsize = (14,6), dpi = 80)
plt.plot(salary, payment, color = 'grey', lw = 2, label = '$f(w,x_i)=w_0 + w_1x_{i1} + w_2x_{i2}$')
plt.plot(df[df['Decision'] == 'Approved']['Salary'], df[df['Decision'] == 'Approved']['Payment'],
'o', color ='green', markersize = 12, label = 'Decision - Loan approved')
plt.plot(df[df['Decision'] == 'Refusal']['Salary'], df[df['Decision'] == 'Refusal']['Payment'],
's', color = 'red', markersize = 12, label = 'Decision - Loan refusal')
plt.xlabel('Salary', size = 16)
plt.ylabel('Payment', size = 16)
plt.legend(prop = {'size': 14})
plt.show()
ãããã£ãŠãé¢æ°ã«åŸã£ãŠæ§ç¯ãããçŽç·ã¯ã ããæªããåãæãšãè¯ããåãæãåºå¥ããŸãã 欲æãšèœåãäžèŽããªãåãæã¯ã©ã€ã³ãäžåã£ãŠããŸãã (Lesha)ãã¢ãã«ã®ãã©ã¡ãŒã¿ã«ããã°ããŒã³ãè¿æžã§ããåãæã¯ã©ã€ã³ãäžåã£ãŠããŸã (Vasya ãš Fedya)ã èšãæããã°ãç§ãã¡ã®çŽç³»ã¯åãæã XNUMX ã€ã®ã¯ã©ã¹ã«åããŠãããšèšããŸãã ãããã次ã®ããã«è¡šããŸãã ããŒã³ãè¿æžããå¯èœæ§ãæãé«ãåãæã次ã®ããã«åé¡ããŸãã ãŸã㯠ããŒã³ãè¿æžã§ããªãå¯èœæ§ãé«ãåãæãå«ããŸãã
ãã®ç°¡åãªäŸããåŸãçµè«ããŸãšããŠã¿ãŸãããã ãã€ã³ããèŠãŠã¿ãŸããã ãããŠãç¹ã®åº§æšã察å¿ããçŽç·ã®æ¹çšåŒã«ä»£å ¥ããŸãã ã次㮠XNUMX ã€ã®ãªãã·ã§ã³ãæ€èšããŠãã ããã
- ç¹ãç·ã®äžã«ããããããã¯ã©ã¹ã«å²ãåœãŠãå Žå ã次ã«é¢æ°ã®å€ ãããã©ã¹ã«ãªããŸã ЎП ã ããã¯ãããŒã³ãè¿æžã§ãã確çã以äžã§ãããšä»®å®ã§ããããšãæå³ããŸãã ã é¢æ°ã®å€ã倧ããã»ã©ã確çãé«ããªããŸãã
- ç¹ãç·ã®äžã«ããããããã¯ã©ã¹ã«å²ãåœãŠãå Žå ãŸã㯠ã®å Žåãé¢æ°ã®å€ã¯è² ã®å€ã«ãªããŸãã ЎП ã 次ã«ãåéè¿æžã®ç¢ºçã以äžã§ãããšä»®å®ããŸãã ãããŠãé¢æ°ã®çµ¶å¯Ÿå€ã倧ããã»ã©ãä¿¡é ŒåºŠã¯é«ããªããŸãã
- ç¹ã¯ XNUMX ã€ã®ã¯ã©ã¹éã®å¢çäžã®çŽç·äžã«ãããŸãã ãã®å Žåãé¢æ°ã®å€ã¯ çãããªããŸã ãããŠããŒã³ãè¿æžãã確çã¯æ¬¡ã®ãšããã§ã .
ããŠãXNUMX ã€ã§ã¯ãªãæ°åãXNUMX ã€ã§ã¯ãªãæ°åã®åãæããããšæ³åããŠã¿ãŸãããã 次ã«ãçŽç·ã®ä»£ããã«æ¬¡ã®ããã«ãªããŸãã m次å å¹³é¢ãšä¿æ° ç§ãã¡ã¯äœããªããšããããå°ãåºãããã®ã§ã¯ãªãããã¹ãŠã®ã«ãŒã«ã«åŸã£ãŠãããŒã³ãè¿æžãããŸãã¯è¿æžããŠããªãåãæã«é¢ããèç©ãããããŒã¿ã«åºã¥ããŠå°ãåºãããŸãã ãããŠå®éãçŸåšãæ¢ç¥ã®ä¿æ°ã䜿çšããŠåãæãéžæããŠããããšã«æ³šæããŠãã ããã ã å®éãããžã¹ãã£ãã¯ååž°ã¢ãã«ã®ã¿ã¹ã¯ã¯ãŸãã«ââãã©ã¡ãŒã¿ã決å®ããããšã§ãã ãæ倱é¢æ°ã®å€ã¯ ç©æµæ倱 æå°éã«æããåŸåã«ãªããŸãã ãã ãããã¯ãã«ã®èšç®æ¹æ³ã«ã€ããŠã¯ã ã詳ããã¯èšäºã® 5 çªç®ã®ã»ã¯ã·ã§ã³ã§èª¬æããŸãã ãã®éã«ãç§ãã¡ã¯çŽæã®å°ãéè¡å®¶ãšåœŒã® XNUMX 人ã®é¡§å®¢ã®å ã«æ»ããŸãã
æ©èœã®ããã㧠ç§ãã¡ã¯èª°ã«èè³ãå¯èœã§ã誰ã«èè³ãæåŠããå¿ èŠãããããç¥ã£ãŠããŸãã ãããããã®ãããªæ å ±ãæã£ãŠãã£ã¬ã¯ã¿ãŒã«è¡ãããšã¯ã§ããŸããã圌ãã¯ç§ãã¡ããååãæã®ããŒã³è¿æžã®å¯èœæ§ãç¥ãããã£ãããã§ãã äœããããïŒ çãã¯ç°¡åã§ããäœããã®æ¹æ³ã§é¢æ°ãå€æããå¿ èŠããããŸãã ããã®å€ã¯ç¯å²å ã«ãããŸã å€ãç¯å²å ã«ããé¢æ°ã« ã ãããŠãã®ãããªé¢æ°ãååšããããã¯åŒã°ããŸã ããžã¹ãã£ãã¯å¿çé¢æ°ãŸãã¯éããžããå€æã äŒãïŒ
ã©ã®ããã«æ©èœãããã段éçã«èŠãŠã¿ãŸããã ããžã¹ãã£ãã¯å¿çé¢æ°ã å察æ¹åã«æ©ãããšã«æ³šæããŠãã ããã ããã®ç¯å²ã«ãã確çå€ãããã£ãŠãããšä»®å®ããŸãã ЎП 次ã«ããã®å€ã次ã®æ°å€ç¯å²å šäœã«ãå·»ãæ»ãããŸãã ЎП .
03. ããžã¹ãã£ãã¯å¿çé¢æ°ãå°åºãã
ã¹ããã 1. 確çå€ãç¯å²ã«å€æãã
é¢æ°ã®å€æäž Ð² ããžã¹ãã£ãã¯å¿çé¢æ° ä¿¡çšã¢ããªã¹ãã®ããšã¯ãã®ãŸãŸã«ããŠã代ããã«ããã¯ã¡ãŒã«ãŒã®ãã¢ãŒã«åå ããŸãã ãããããã¡ãããè³ãã¯ããŸãããç§ãã¡ãèå³ãæã£ãŠããã®ã¯ããã®åŒã®æå³ã ãã§ããããšãã°ããã£ã³ã¹ã¯ 4 察 1 ã§ãããã¹ãŠã®ããã¿ãŒã«ãšã£ãŠããªãã¿ã®ãªããºã¯ããæåããšããã®æ¯çã§ãã倱æãã 確çã®çšèªã§ã¯ããªããºãšã¯ãã€ãã³ããçºçãã確çãã€ãã³ããçºçããªã確çã§å²ã£ããã®ã§ãã åºæ¥äºãèµ·ãã確çã®èšç®åŒãæžããŠã¿ãŸããã :
ã©ã - äºè±¡ãçºçãã確çã â ã€ãã³ããçºçããªã確ç
ããšãã°ãããŽã§ããã¯ããšãããã åã®è¥ããŠåŒ·ããŠéã³å¿ã®ãã銬ããã¬ãŒã¹ã§ãããã«ãããšããååã®ãããã 幎èããè婊人ã«åã€ç¢ºçã次ã®ãšããã§ãããšããŸãã ã®å ŽåããVeterokãã®æå確çã¯æ¬¡ã®ããã«ãªããŸãã к éãåæ§ã§ããªããºããããã°ã確çãèšç®ããã®ã¯é£ãããããŸããã :
ãããã£ãŠãç§ãã¡ã¯ç¢ºçããã£ã³ã¹ã«ãå€æãããããšãåŠã³ãŸããã ЎП ã ããäžæ©é²ãã§ã確çã次ã®æ°çŽç·å šäœã«ãå€æãããæ¹æ³ãåŠã³ãŸãããã ЎП .
ã¹ããã 2. 確çå€ãç¯å²ã«å€æãã
ãã®ã¹ãããã¯éåžžã«ç°¡åã§ãããªããºã®å¯Ÿæ°ããªã€ã©ãŒæ°ã®åºã«æ±ããŸãã ãããŠæ¬¡ã®ããã«ãªããŸã:
ããã§ã次ã®ããšãããããŸãã ãå€ãèšç®ããŸã éåžžã«ã·ã³ãã«ã§ãããã«ããžãã£ããªãã®ã«ãªãã¯ãã§ãã ã ããã¯æ¬åœã§ãã
奜å¥å¿ãããã©ããªããã確èªããŠã¿ãŸããã ã®å Žåãè² ã®å€ã衚瀺ãããããšãæåŸ ãããŸãã ã ç§ãã¡ã¯ä»¥äžããã§ãã¯ããŸã: ã ããã¯æ£ããã
ããã§ã確çå€ã次ããå€æããæ¹æ³ãããããŸããã ЎП ããã®æ°çŽç·å šäœã«æ²¿ã£ãŠ ЎП ã 次ã®ã¹ãããã§ã¯ããã®éã®ããšãè¡ããŸãã
ä»ã®ãšããã察æ°ã®æ³åã«åŸã£ãŠãé¢æ°ã®å€ãããã£ãŠããããšã«æ³šæããŠãã ããã ããªããºãèšç®ã§ããŸãã
ãªããºã決å®ãããã®æ¹æ³ã¯ã次ã®ã¹ãããã§åœ¹ç«ã¡ãŸãã
ã¹ããã 3. ã決å®ããããã®åŒãå°ãåºããŸããã
ããã§ç§ãã¡ã¯åŠã³ãç¥ããŸãã ãé¢æ°å€ãæ€çŽ¢ããŸã ã ããããå®éã«ã¯ããŸã£ããéã®ããšãå¿ èŠã§ããã€ãŸãã䟡å€ãç¥ãããšã§ãã èŠã€ãã ã ãããè¡ãã«ã¯ã次ã®ãããªéãªããºé¢æ°ãªã©ã®æŠå¿µã«ç®ãåããŸãããã
ãã®èšäºã§ã¯ãäžèšã®åŒãå°ãåºããŸããããäžèšã®äŸã®æ°å€ã䜿çšããŠç¢ºèªããŸãã ãªããºã¯ 4 察 1 ()ãã€ãã³ããçºçãã確ç㯠0.8 (ïŒã 眮ãæããŠã¿ãŸããã: ã ããã¯ã以åã«å®è¡ããèšç®ãšäžèŽããŸãã 次ãžç§»ããŸãããã
æåŸã®ã¹ãããã§æ¬¡ã®ããã«æšæž¬ããŸããã ããã¯ãéãªããºé¢æ°ã§çœ®æãè¡ãããšãã§ããããšãæå³ããŸãã æã ãåŸãïŒ
ååãšåæ¯ã®äž¡æ¹ã次ã®å€ã§å²ããŸãã 次ã«ïŒ
念ã®ãããã©ãã«ãééãããªããã確èªããããã«ããã 2 åå°ããªãã§ãã¯ãè¡ããŸãã ã¹ããã XNUMX ã§ã¯ã ãšå€æãã ã 次ã«ãå€ãä»£å ¥ããŸã ããžã¹ãã£ãã¯å¿çé¢æ°ã«ä»£å ¥ãããšã次ã®çµæãåŸããããšæåŸ ãããŸãã ã 眮ãæãããšæ¬¡ã®ããã«ãªããŸãã
èªè ã®çãããããã§ãšãããããŸããããžã¹ãã£ãã¯å¿çé¢æ°ãå°åºãããã¹ãããŸããã é¢æ°ã®ã°ã©ããèŠãŠã¿ãŸãããã
ã°ã©ã3ãããžã¹ãã£ãã¯å¿çé¢æ°ã
ã°ã©ããæç»ããã³ãŒã
import math
def logit (f):
return 1/(1+math.exp(-f))
f = np.arange(-7,7,0.05)
p = []
for i in f:
p.append(logit(i))
fig, axes = plt.subplots(figsize = (14,6), dpi = 80)
plt.plot(f, p, color = 'grey', label = '$ 1 / (1+e^{-w^Tx_i})$')
plt.xlabel('$f(w,x_i) = w^Tx_i$', size = 16)
plt.ylabel('$p_{i+}$', size = 16)
plt.legend(prop = {'size': 14})
plt.show()
æç®ã§ã¯ããã®é¢æ°ã®ååã次ã®ããã«èŠã€ããããšãã§ããŸãã ã·ã°ã¢ã€ãé¢æ°ã ãã®ã°ã©ãã¯ããªããžã§ã¯ããã¯ã©ã¹ã«å±ãã確çã®äž»ãªå€åãæ¯èŒççãç¯å²å ã§çºçããããšãæ確ã«ç€ºããŠããŸãã ãã©ãããã ЎП .
ä¿¡çšã¢ããªã¹ãã«æ»ã£ãŠãããŒã³è¿æžã®å¯èœæ§ã®èšç®ãæäŒã£ãŠãããããšããå§ãããŸããããããªããšãããŒãã¹ãªãã§åãæ®ãããå±éºããããŸã:)
è¡š 2 ãæœåšçãªåãæã
ããŒãã«ãçæããã³ãŒã
proba = []
for i in df['f(w,x)']:
proba.append(round(logit(i),2))
df['Probability'] = proba
df[['The borrower', 'Salary', 'Payment', 'f(w,x)', 'Decision', 'Probability']]
ããã§ãããŒã³è¿æžã®ç¢ºçãæ±ããŸããã äžè¬ã«ãããã¯çå®ã§ããããã§ãã
å®éã絊äžã 120.000 RUR ã® Vasya ãæ¯æ 3.000 RUR ãéè¡ã«æž¡ãããšãã§ãã確ç㯠100% ã«è¿ãã§ãã ãšããã§ãéè¡ã®æ¹éã§ãããšãã°ããŒã³è¿æžã®ç¢ºçãããšãã° 0.3 ãè¶ ãã顧客ãžã®èè³ãèŠå®ããŠããå Žåãéè¡ã¯ Lesha ã«èè³ãå®è¡ã§ããããšãç解ããå¿ èŠããããŸãã ãã ããã®å Žåãéè¡ã¯èµ·ããåŸãæ倱ã«åããŠãã倧ããªåŒåœéãäœæããŸãã
ãŸãã絊äžå¯Ÿæ¯ææ¯çã¯å°ãªããšã 3 ã§ã5.000 RUR ã®ããŒãžã³ãäžéããåŒãããŠããããšã«ã泚æããŠãã ããã ãããã£ãŠãéã¿ã®ãã¯ãã«ãå ã®åœ¢åŒã§äœ¿çšããããšã¯ã§ããŸããã§ããã ã ä¿æ°ãå€§å¹ ã«æžããå¿ èŠãããããã®å Žåã¯åä¿æ°ã 25.000 ã§é€ç®ããŸãããã€ãŸããçµæã調æŽããŸããã ãã ããããã¯ç¹ã«åæ段éã§ã®å 容ã®ç解ã容æã«ããããã«è¡ãããŸããã 人çã§ã¯ãä¿æ°ãçºæããã調æŽãããããå¿ èŠã¯ãªããä¿æ°ãèŠã€ããå¿ èŠããããŸãã ãã®èšäºã®æ¬¡ã®ã»ã¯ã·ã§ã³ã§ã¯ããã©ã¡ãŒã¿ãéžæããããã®æ¹çšåŒãå°ãåºããŸãã .
04. éã¿ãã¯ãã«ã決å®ããããã®æå°äºä¹æ³ ããžã¹ãã£ãã¯å¿çé¢æ°ã§
éã¿ã®ãã¯ãã«ãéžæãããã®æ¹æ³ã¯ãã§ã«ç¥ã£ãŠããŸã ãšã㊠æå°äºä¹æ³ (LSM) å®éãäºé åé¡åé¡ã§ããã䜿çšããŠã¿ãŠã¯ãããã§ãããã? 確ãã«ã䜿çšã劚ãããã®ã¯äœããããŸãã MNCãåé¡åé¡ã§ã¯ãã®æ¹æ³ã®ã¿ãã以äžã®æ¹æ³ããã粟床ã®äœãçµæããããããŸãã ç©æµæ倱ã ããã«ã¯çè«çæ ¹æ ããããŸãã ãŸãç°¡åãªäŸã XNUMX ã€èŠãŠã¿ãŸãããã
ç§ãã¡ã®ã¢ãã«ïŒã䜿çšãããšã MSE О ç©æµæ倱) ãã§ã«éã¿ã®ãã¯ãã«ã®éžæãéå§ããŠããŸã ãããŠãã段éã§èšç®ãäžæ¢ããŸããã äžéãæåŸããŸãã¯æåã®ãããã§ãã£ãŠããéèŠãªããšã¯ãéã¿ã®ãã¯ãã«ã®å€ããã§ã«ããã€ããããšããããšã§ãããã®ã¹ãããã§ã¯ãéã¿ã®ãã¯ãã«ã¯ äž¡æ¹ã®ã¢ãã«ã«éãã¯ãããŸããã 次ã«ãçµæã®éã¿ãååŸããŠæ¬¡ã®ããã«ä»£å ¥ããŸãã ããžã¹ãã£ãã¯å¿çé¢æ° () ã¯ã©ã¹ã«å±ãããªããžã§ã¯ãã®å Žå ã éžæããéã¿ãã¯ãã«ã«åŸã£ãŠãã¢ãã«ãéåžžã«ééã£ãŠããå Žåãšãã®éã® XNUMX ã€ã®ã±ãŒã¹ã調ã¹ãŸããã¢ãã«ã¯ããªããžã§ã¯ãããã®ã¯ã©ã¹ã«å±ããŠãããšåŒ·ã確信ããŠããŸãã ã 䜿çšããå Žåã«ã©ã®ãããªçœ°éã課ãããã®ãèŠãŠã¿ãŸããã MNC О ç©æµæ倱.
䜿çšãããæ倱é¢æ°ã«å¿ããŠããã«ãã£ãèšç®ããã³ãŒã
# клаÑÑ ÐŸÐ±ÑекÑа
y = 1
# веÑПÑÑМПÑÑÑ ÐŸÑМеÑÐµÐœÐžÑ ÐŸÐ±ÑекÑа к клаÑÑÑ Ð² ÑППÑвеÑÑÑвОО Ñ Ð¿Ð°ÑаЌеÑÑаЌО w
proba_1 = 0.01
MSE_1 = (y - proba_1)**2
print 'КÑÑÐ°Ñ MSE пÑО гÑÑбПй ПÑОбке =', MSE_1
# МапОÑеЌ ÑÑМкÑÐžÑ ÐŽÐ»Ñ Ð²ÑÑОÑÐ»ÐµÐœÐžÑ f(w,x) пÑО ОзвеÑÑМПй веÑПÑÑМПÑÑО ПÑМеÑÐµÐœÐžÑ ÐŸÐ±ÑекÑа к клаÑÑÑ +1 (f(w,x)=ln(odds+))
def f_w_x(proba):
return math.log(proba/(1-proba))
LogLoss_1 = math.log(1+math.exp(-y*f_w_x(proba_1)))
print 'КÑÑÐ°Ñ Log Loss пÑО гÑÑбПй ПÑОбке =', LogLoss_1
proba_2 = 0.99
MSE_2 = (y - proba_2)**2
LogLoss_2 = math.log(1+math.exp(-y*f_w_x(proba_2)))
print '**************************************************************'
print 'КÑÑÐ°Ñ MSE пÑО ÑОлÑМПй ÑвеÑеММПÑÑО =', MSE_2
print 'КÑÑÐ°Ñ Log Loss пÑО ÑОлÑМПй ÑвеÑеММПÑÑО =', LogLoss_2
倱æäŸ â ã¢ãã«ã¯ãªããžã§ã¯ããã¯ã©ã¹ã«å²ãåœãŠãŸã 0,01ã®ç¢ºçã§
䜿çšæã®ããã«ã㣠MNC ã«ãªããŸãïŒ
䜿çšæã®ããã«ã㣠ç©æµæ倱 ã«ãªããŸãïŒ
匷ãèªä¿¡ã®äºäŸ â ã¢ãã«ã¯ãªããžã§ã¯ããã¯ã©ã¹ã«å²ãåœãŠãŸã 0,99ã®ç¢ºçã§
䜿çšæã®ããã«ã㣠MNC ã«ãªããŸãïŒ
䜿çšæã®ããã«ã㣠ç©æµæ倱 ã«ãªããŸãïŒ
ãã®äŸã¯ãé倧ãªãšã©ãŒã®å Žåãæ倱é¢æ°ã ãã°ãã¹ ã¢ãã«ã«ä»¥äžã®ããã«ãã£ãå€§å¹ ã«èª²ã MSEã ããã§ãæ倱é¢æ°ã䜿çšããçè«çèæ¯ãäœã§ããããç解ããŸãããã ãã°ãã¹ åé¡åé¡ã§ã
05. æå°€æ³ãšããžã¹ãã£ãã¯ååž°
åé ã§çŽæããããã«ããã®èšäºã«ã¯ç°¡åãªäŸãè±å¯ã«ãããŸãã ã¹ã¿ãžãªã«ã¯ãå¥ã®äŸãšå€ãã²ã¹ããéè¡ã®åãæããŽã¡ã·ã£ããã§ãã£ã¢ãã¬ã·ã£ãããŸãã
念ã®ãããäŸãéçºããåã«ãç§ãã¡ã¯äººçã«ãããŠãæ°åãŸãã¯æ°çŸã®ç¹åŸŽãæã€æ°åãŸãã¯æ°çŸäžã®ãªããžã§ã¯ãã®ãã¬ãŒãã³ã° ãµã³ãã«ãæ±ã£ãŠããããšãæãåºãããŠãã ããã ãã ããããã§ã®æ°å€ã¯ãåå¿è ã®ããŒã¿ ãµã€ãšã³ãã£ã¹ãã®é ã«ç°¡åã«åãŸãããã«åãããŠããŸãã
äŸã«æ»ããŸãããã ã¢ã«ãŽãªãºã ããªãŒã·ã£ã«ã¯ããŒã³ãçºè¡ããªãããã«æ瀺ããã«ãããããããéè¡ã®åç· åœ¹ãå°ã£ãŠããäººå šå¡ã«ããŒã³ãçºè¡ããããšã決å®ãããšæ³åããŠã¿ãŸãããã ãããŠä»ãååãªæéãçµéããXNUMX 人ã®è±éã®ãã¡èª°ãããŒã³ãè¿æžãã誰ãè¿æžããªãã£ãã®ããããããŸããã äºæ³ãããŠããããšïŒãŽã¡ã·ã£ãšãã§ãã£ã¢ã¯ããŒã³ãè¿æžããŸãããããªãŒã·ã£ã¯è¿æžããŸããã§ããã ããã§ããã®çµæãç§ãã¡ã«ãšã£ãŠæ°ãããã¬ãŒãã³ã° ãµã³ãã«ã«ãªããšæ³åããŠã¿ãŸããããåæã«ãããããããŒã³è¿æžã®å¯èœæ§ã«åœ±é¿ãäžããèŠçŽ (åãæã®çµŠäžãæ¯æã®æ¯æãé¡) ã«é¢ãããã¹ãŠã®ããŒã¿ãæ¶ãããã®ããã§ãã 次ã«ãçŽæçã«ã¯ãåãæã® XNUMX 人㫠XNUMX 人ãéè¡ã«ããŒã³ãè¿æžããªããšä»®å®ã§ããŸããèšãæããã°ã次ã®åãæãããŒã³ãè¿æžãã確çã¯æ¬¡ã®ãšããã§ãã ã ãã®çŽæçãªä»®å®ã«ã¯çè«çãªè£ä»ããããã以äžã«åºã¥ããŠããŸãã æå°€æ³ãæç®ã§ã¯ããããåŒã°ããŠããŸãã æå°€åç.
ãŸããæŠå¿µçãªè£ 眮ã«ã€ããŠç解ããŸãããã
ãµã³ããªã³ã°ã®å°€åºŠ ãŸãã«ãã®ãããªãµã³ãã«ãåŸããã確çãã€ãŸããŸãã«ãã®ãããªèŠ³å¯/çµæãåŸããã確çã§ãã åãµã³ãã«çµæãååŸãã確çã®ç© (ããšãã°ãVasyaãFedyaãLesha ã®ããŒã³ãåæã«è¿æžããããã©ãã)ã
尀床é¢æ° ãµã³ãã«ã®å¯èœæ§ãååžãã©ã¡ãŒã¿ã®å€ã«é¢é£ä»ããŸãã
ç§ãã¡ã®å Žåããã¬ãŒãã³ã° ãµã³ãã«ã¯äžè¬åããããã«ããŒã€ ã¹ããŒã ã§ããã確çå€æ°ã¯æ¬¡ã® XNUMX ã€ã®å€ã®ã¿ãåããŸãã ãŸã㯠ã ãããã£ãŠããµã³ãã«ã®å°€åºŠã¯ãã©ã¡ãŒã¿ã®å°€åºŠé¢æ°ãšããŠæžãããšãã§ããŸãã 次ã®ããã«ããŸãã
äžèšã®ãšã³ããªã¯æ¬¡ã®ããã«è§£éã§ããŸãã Vasya ãš Fedya ãããŒã³ãè¿æžããå ±å確çã¯æ¬¡ã®ãšããã§ãã ããªãŒã·ã£ãããŒã³ãè¿æžããªã確çã¯æ¬¡ã®ãšããã§ãã (èµ·ãã£ãã®ã¯ããŒã³ã®è¿æžã§ã¯ãªããã)ããããã£ãŠãXNUMX ã€ã®ã€ãã³ããã¹ãŠã®åæ確çã¯çããã§ãã .
æå°€æ³ æªç¥ã®ãã©ã¡ãŒã¿ãæ倧åããããšã§æšå®ããææ³ã§ãã 尀床é¢æ°ã ç§ãã¡ã®å Žåããã®ãããªå€ãèŠã€ããå¿ èŠããããŸã ã©ã㧠æ倧å€ã«éããŸãã
尀床é¢æ°ãæ倧å€ã«éããæªç¥ã®ãã©ã¡ãŒã¿ã®å€ãæ¢ããšããå®éã®ã¢ã€ãã¢ã¯ã©ãããæ¥ãã®ã§ãããã? ãã®ã¢ã€ãã¢ã®èµ·æºã¯ããµã³ãã«ãæ¯éå£ã«ã€ããŠç§ãã¡ãå©çšã§ããå¯äžã®æ å ±æºã§ãããšããèãã«ç±æ¥ããŠããŸãã æ¯éå£ã«ã€ããŠç§ãã¡ãç¥ã£ãŠãããã¹ãŠããµã³ãã«ã«è¡šçŸãããŠããŸãã ãããã£ãŠãç§ãã¡ãèšããããšã¯ããµã³ãã«ã¯ç§ãã¡ãå©çšã§ããæ¯éå£ãæãæ£ç¢ºã«åæ ããŠãããšããããšã ãã§ãã ãããã£ãŠãå©çšå¯èœãªãµã³ãã«ã®å¯èœæ§ãæãé«ããªããã©ã¡ãŒã¿ãèŠã€ããå¿ èŠããããŸãã
æããã«ãç§ãã¡ã¯é¢æ°ã®æ¥µå€ç¹ãèŠã€ããå¿ èŠãããæé©ååé¡ãæ±ã£ãŠããŸãã 極å€ç¹ãèŠã€ããã«ã¯ãäžæ¬¡æ¡ä»¶ãèæ ®ããå¿ èŠããããŸããã€ãŸããé¢æ°ã®å°é¢æ°ããŒãã«çãããšã¿ãªããŠãç®çã®ãã©ã¡ãŒã¿ãŒã«é¢ããŠæ¹çšåŒã解ãå¿ èŠããããŸãã ãã ããå€æ°ã®å åã®ç©ã®å°é¢æ°ãæ±ããã®ã¯æéã®ãããäœæ¥ã«ãªãå¯èœæ§ãããããããããåé¿ããã«ã¯ã察æ°ã«åãæ¿ãããšããç¹å¥ãªãã¯ããã¯ããããŸãã 尀床é¢æ°ã ãªããã®ãããªç§»è¡ãå¯èœãªã®ã§ãããã? é¢æ°èªäœã®æ¥µå€ãæ¢ããŠããããã§ã¯ãªãããšã«æ³šæããŠãã ããããããã³æ¥µå€ç¹ãã€ãŸãæªç¥ã®ãã©ã¡ãŒã¿ã®å€ ã©ã㧠æ倧å€ã«éããŸãã 察æ°ã¯å調é¢æ°ã§ããããã察æ°ã«ç§»è¡ããå Žåã極å€ç¹ã¯å€ãããŸãã (極å€èªäœã¯ç°ãªããŸãã)ã
äžèšã«åŸã£ãŠãVasyaãFedyaãLesha ããã®ããŒã³ã䜿çšããŠäŸãéçºãç¶ããŸãããã ãŸãã¯æ¬¡ãžé²ã¿ãŸããã 尀床é¢æ°ã®å¯Ÿæ°:
ããã§ã次ã®ããã«åŒãç°¡åã«åºå¥ã§ããŸãã :
ãããŠæåŸã«ãäžæ¬¡æ¡ä»¶ãæ€èšããŸããé¢æ°ã®å°é¢æ°ããŒããšã¿ãªããŸãã
ãããã£ãŠãããŒã³è¿æžã®ç¢ºçã«ã€ããŠã®çŽæçãªæšå®ã¯ã çè«çã«ã¯æ£åœåãããŸããã
ããã¯ããã®ã§ããããã®æ å ±ãä»ã©ãããã°ããã§ãããã? åãæã® XNUMX 人㫠XNUMX 人ãéè¡ã«ãéãè¿ããªããšä»®å®ãããšãéè¡ã¯å¿ ç¶çã«ç Žç£ããããšã«ãªããŸãã ããã§ãããããã¯ããŒã³è¿æžã®ç¢ºçã以äžãšçãããšè©äŸ¡ããå Žåã«éããŸãã ããŒã³è¿æžã«åœ±é¿ãäžããèŠå ãã€ãŸãåãæã®çµŠäžãæã ã®æ¯æãé¡ã¯èæ ®ããŠããŸããã 以åã«ãããããšåãèŠçŽ ãèæ ®ããŠãå顧客ã«ããããŒã³ã®è¿æžç¢ºçãèšç®ããããšãæãåºããŠãã ããã å®æ°ãšç°ãªã確çãåŸãããã®ã¯è«ççã§ãã .
ãµã³ãã«ã®å¯èœæ§ãå®çŸ©ããŸãããã
ãµã³ãã«ã®å°€åºŠãèšç®ããã³ãŒã
from functools import reduce
def likelihood(y,p):
line_true_proba = []
for i in range(len(y)):
ltp_i = p[i]**y[i]*(1-p[i])**(1-y[i])
line_true_proba.append(ltp_i)
likelihood = []
return reduce(lambda a, b: a*b, line_true_proba)
y = [1.0,1.0,0.0]
p_log_response = df['Probability']
const = 2.0/3.0
p_const = [const, const, const]
print 'ÐÑавЎПпПЎПбОе вÑбПÑкО пÑО кПМÑÑаМÑМПЌ зМаÑеМОО p=2/3:', round(likelihood(y,p_const),3)
print '****************************************************************************************************'
print 'ÐÑавЎПпПЎПбОе вÑбПÑкО пÑО ÑаÑÑеÑМПЌ зМаÑеМОО p:', round(likelihood(y,p_log_response),3)
äžå®å€ã§ã®ãµã³ãã«å°€åºŠ :
èŠå ãèæ ®ããŠããŒã³è¿æžã®ç¢ºçãèšç®ããéã®ãµã³ãã«å°€åºŠ :
èŠå ã«å¿ããŠèšç®ããã確çãæã€ãµã³ãã«ã®å°€åºŠã¯ãäžå®ã®ç¢ºçå€ãæã€å°€åºŠãããé«ãããšãå€æããŸããã ããã¯ã©ãããæå³ã§ããïŒ ããã¯ãèŠå ã«é¢ããç¥èã«ãããå顧客ã®ããŒã³è¿æžã®ç¢ºçãããæ£ç¢ºã«éžæã§ããããã«ãªã£ããšããããšã瀺åããŠããŸãã ãããã£ãŠã次ã®èè³ãå®è¡ãããšãã¯ããã®èšäºã®ã»ã¯ã·ã§ã³ 3 ã®æåŸã§ææ¡ãããŠããã¢ãã«ã䜿çšããŠåéè¿æžã®å¯èœæ§ãè©äŸ¡ããã®ãããæ£ç¢ºã§ãã
ããããæ倧åãããå Žåã¯ã ãµã³ãã«å°€åºŠé¢æ°ã§ã¯ãVasyaãFedyaãLesha ã®ç¢ºçããããã 0.99ã0.99ã0.01 ã«çããããã¢ã«ãŽãªãºã ã䜿çšããŠã¿ãŠã¯ãããã§ããããã ããããããã®ãããªã¢ã«ãŽãªãºã ã¯ããµã³ãã«ã®å°€åºŠå€ã次ã®å€ã«è¿ã¥ããããããã¬ãŒãã³ã° ãµã³ãã«ã§ããŸãæ©èœããã§ãããã ãããã第äžã«ããã®ãããªã¢ã«ãŽãªãºã ã¯äžè¬åèœåã«åé¡ãããå¯èœæ§ãé«ãã第äºã«ããã®ã¢ã«ãŽãªãºã ã¯æããã«ç·åœ¢ã§ã¯ãããŸããã ãããŠããªãŒããŒãã¬ãŒãã³ã° (åæ§ã«åŒ±ãæ±åèœå) ã«å¯Ÿæããæ¹æ³ãæããã«ãã®èšäºã®èšç»ã«å«ãŸããŠããªãå Žåã¯ã2.5 çªç®ã®ç¹ãããã«è©³ããèŠãŠã¿ãŸãããã ãããè¡ãã«ã¯ãç°¡åãªè³ªåã«çããã ãã§ãã ç§ãã¡ãç¥ã£ãŠããèŠå ãèæ ®ãããšããŽã¡ã·ã£ãšãã§ãã£ã¢ãããŒã³ãè¿æžãã確çã¯åãã«ãªãã§ãããã? å¥å šãªè«çã®èŠ³ç¹ããèšãã°ããã¡ããããã§ã¯ãããŸããã ãããã£ãŠãVasyaã¯ããŒã³ãè¿æžããããã«æ¯æ絊äžã®27,8ïŒ ãæ¯æããFedyaã¯ã»ãŒ2ïŒ ãæ¯æããŸãã ãŸããã°ã©ã XNUMXãã¯ã©ã€ã¢ã³ãã®åé¡ãã§ã¯ãVasya ã Fedya ãããã¯ã©ã¹ãåããç·ããã¯ããã«é¢ããŠããããšãããããŸãã ãããŠæåŸã«ãé¢æ°ã Vasya ãš Fedya ã§ã¯ç°ãªãå€ã䜿çšãããŸããVasya ã§ã¯ 4.24ãFedya ã§ã¯ 1.0 ã§ãã ããã§ãããšãã°ãFedya ã®åå ¥ãæ¡éãã«å€ãã£ãå ŽåããŸãã¯ããå°ãªãèè³ãèŠæ±ããå ŽåãVasya ãš Fedya ã®ããŒã³ãè¿æžãã確çã¯åçã«ãªããŸãã èšãæããã°ãç·åœ¢äŸåæ§ã¯éšãããªããšããããšã§ãã ãããŠå®éã«ãªããºãèšç®ããŠã¿ããš ããããŠäœããªããšããããããããæã¡åºããããã§ã¯ãããŸããããç§ãã¡ã®äŸ¡å€èŠ³ã¯å®å šã§ãããšèšããŸãã ååãæã«ããããŒã³ã®è¿æžç¢ºçãæšå®ã§ããã®ãæåã§ãããä¿æ°ã®æ±ºå®ã¯æ¬¡ã®ãšããã§ãããšä»®å®ããããšã«åæããããã ãã¹ãŠã®ã«ãŒã«ã«åŸã£ãŠå®è¡ãããå Žåã¯ããã®ããã«ä»®å®ããŸããä¿æ°ã䜿çšãããšã確çãããæ£ç¢ºã«æšå®ã§ããŸã:)
ãããã話ã¯ãããŸãã ãã®ã»ã¯ã·ã§ã³ã§ã¯ãéã¿ã®ãã¯ãã«ãã©ã®ããã«æ±ºå®ãããããç解ããå¿ èŠããããŸãã ãååãæã«ããããŒã³ã®è¿æžå¯èœæ§ãè©äŸ¡ããããã«å¿ èŠã§ãã
ã©ã®ãããªæŠåšã䜿ã£ãŠãªããºãæ¢ãã®ããç°¡åã«ãŸãšããŠã¿ãŸããã :
1. 察象å€æ°ïŒäºæž¬å€ïŒãšçµæã«åœ±é¿ãäžããèŠå ãšã®é¢ä¿ã¯ç·åœ¢ã§ãããšä»®å®ããŸãã ãã®ãããªçç±ã§äœ¿çšãããã®ã§ã ç·åœ¢ååž°é¢æ° çš® ããã®è¡ã¯ãªããžã§ã¯ã (ã¯ã©ã€ã¢ã³ã) ãã¯ã©ã¹ã«åå²ããŸãã О ãŸã㯠ïŒããŒã³ãè¿æžã§ãã顧客ãšããã§ãªã顧客ïŒã ç§ãã¡ã®å Žåãæ¹çšåŒã®åœ¢åŒã¯æ¬¡ã®ãšããã§ãã .
2.䜿çšããŸã éããžããé¢æ° çš® ãªããžã§ã¯ããã¯ã©ã¹ã«å±ãã確çã決å®ãã .
3. ç§ãã¡ã¯ããã¬ãŒãã³ã°ã»ãããäžè¬åããããã¬ãŒãã³ã°ã®å®è£ ãšããŠèããŠããŸãã ãã«ããŒã€ ã¹ããŒã ã€ãŸãããªããžã§ã¯ãããšã«ç¢ºçå€æ°ãçæãããŸãã (ãªããžã§ã¯ãããšã«ç¬èªã®ãã®) ã¯å€ 1 ããšãã確ç㧠- 0ã
4. æ倧åããããã«äœãå¿ èŠããç¥ã£ãŠããŸã ãµã³ãã«å°€åºŠé¢æ° å©çšå¯èœãªãµã³ãã«ãæã劥åœãªãã®ã«ãªãããã«ãåãå ¥ããããŠããèŠçŽ ãèæ ®ã«å ¥ããŸãã èšãæããã°ããµã³ãã«ãæã劥åœã§ãããšæããããã©ã¡ãŒã¿ãéžæããå¿ èŠããããŸãã ãã®å Žåãéžæãããã©ã¡ãŒã¿ãŒã¯ããŒã³è¿æžã®ç¢ºçã§ãã ãããã¯æªç¥ã®ä¿æ°ã«äŸåããŸã ã ãããã£ãŠããã®ãããªéã¿ã®ãã¯ãã«ãèŠã€ããå¿ èŠããããŸã ããã®æç¹ã§ãµã³ãã«ã®å°€åºŠãæ倧ã«ãªããŸãã
5. ç§ãã¡ã¯äœãæ倧åãã¹ãããç¥ã£ãŠããŸã ãµã³ãã«å°€åºŠé¢æ° 䜿çšããããšãã§ã æå°€æ³ã ãããŠãç§ãã¡ã¯ãã®æ¹æ³ã䜿çšããããã®é£ããããªãã¯ããã¹ãŠç¥ã£ãŠããŸãã
ãã®ããã«ããŠãè€æ°ã®ã¹ããããèžãå¿ èŠãããããšãããããŸã:)
ããã§ãèšäºã®åé 㧠XNUMX çš®é¡ã®æ倱é¢æ°ãå°åºããããšããããšãæãåºããŠãã ããã ç©æµæ倱 ãªããžã§ã¯ãã¯ã©ã¹ã®æå®æ¹æ³ã«å¿ããŠç°ãªããŸãã å¶ç¶ã«ããXNUMX ã€ã®ã¯ã©ã¹ãå«ãåé¡åé¡ã§ã¯ãã¯ã©ã¹ã¯æ¬¡ã®ããã«è¡šãããŸãã О ãŸã㯠ã è¡šèšæ³ã«å¿ããŠãåºåã«ã¯å¯Ÿå¿ããæ倱é¢æ°ãå«ãŸããŸãã
ã±ãŒã¹ 1. ãªããžã§ã¯ãã®åé¡ Ðž
以åã¯ããµã³ãã«ã®å¯èœæ§ã決å®ãããšãã«ãåãæã«ããåéè¿æžã®ç¢ºçãä¿æ°ãšäžããããä¿æ°ã«åºã¥ããŠèšç®ãããŸããã ã次ã®åŒãé©çšããŸããã
å®éã« æå³ã¯ ããžã¹ãã£ãã¯å¿çé¢æ° æå®ãããéã¿ãã¯ãã«ã«å¯ŸããŠ
ããããã°ã次ã®ããã«ãµã³ãã«å°€åºŠé¢æ°ãæžãããšã劚ãããã®ã¯äœããããŸããã
äžéšã®åå¿è ã¢ããªã¹ãã«ãšã£ãŠããã®é¢æ°ãã©ã®ããã«æ©èœããããããã«ç解ããããšãé£ããå ŽåããããŸãã ãã¹ãŠãæ確ã«ãã 4 ã€ã®çãäŸãèŠãŠã¿ãŸãããã
1. ãã (ã€ãŸãããã¬ãŒãã³ã° ãµã³ãã«ã«ããã°ããªããžã§ã¯ãã¯ã¯ã©ã¹ +1 ã«å±ããŸã)ãããã³ã¢ã«ãŽãªãºã ãªããžã§ã¯ããã¯ã©ã¹ã«åé¡ãã確çã決å®ããŸã ã 0.9 ã«çããå Žåããã®ãµã³ãã«å°€åºŠã¯æ¬¡ã®ããã«èšç®ãããŸãã
2. ãã ãš ã®å Žåãèšç®ã¯æ¬¡ã®ããã«ãªããŸãã
3. ãã ãš ã®å Žåãèšç®ã¯æ¬¡ã®ããã«ãªããŸãã
4. ãã ãš ã®å Žåãèšç®ã¯æ¬¡ã®ããã«ãªããŸãã
尀床é¢æ°ãã±ãŒã¹ 1 ãš 3ããŸãã¯äžè¬çãªã±ãŒã¹ã§ããªããžã§ã¯ããã¯ã©ã¹ã«å²ãåœãŠã確çã®æ£ããæšæž¬ãããå€ã§æ倧åãããããšã¯æããã§ãã .
ãªããžã§ã¯ããã¯ã©ã¹ã«å²ãåœãŠã確çã決å®ãããšãã ä¿æ°ã ããããããªã ãããããããããæ¢ããŸãã äžã§è¿°ã¹ãããã«ãããã¯æé©ååé¡ã§ãããæåã«éã¿ã®ãã¯ãã«ã«é¢ãã尀床é¢æ°ã®å°é¢æ°ãèŠã€ããå¿ èŠããããŸãã ã ãã ããæåã«èªåèªèº«ã§ã¿ã¹ã¯ãåçŽåããããšã¯çã«ããªã£ãŠããŸãã察æ°ã®å°é¢æ°ãæ¢ããŸãã 尀床é¢æ°.
ãªã察æ°ã®åŸã«ã ããžã¹ãã£ãã¯èª€å·®é¢æ°ããçæ¿ãå€æŽããŸããã Ма ã ã¢ãã«ã®å質ãè©äŸ¡ããåé¡ã§ã¯é¢æ°ã®å€ãæå°åããã®ãäžè¬çã§ããããããã¹ãŠãåçŽã§ããåŒã®å³èŸºã«æ¬¡ã®å€ãæããŸãã ãããã£ãŠãé¢æ°ãæ倧åãã代ããã«ãé¢æ°ãæå°åããŸãã
å®ã¯ä»ãããªãã®ç®ã®åã§ãæ倱é¢æ°ãèŠå¿ããŠå°åºãããŠããã®ã§ã - ç©æµæ倱 XNUMX ã€ã®ã¯ã©ã¹ãå«ããã¬ãŒãã³ã° ã»ããã®å Žå: О .
ããŠãä¿æ°ãèŠã€ããã«ã¯ãå°é¢æ°ãèŠã€ããã ãã§ãã ããžã¹ãã£ãã¯èª€å·®é¢æ° 次ã«ãåŸé éäžæ³ã確ççåŸé éäžæ³ãªã©ã®æ°å€æé©åææ³ã䜿çšããŠãæé©ãªä¿æ°ãéžæããŸãã ã ãã ãããã®èšäºã¯ããªãã®éã§ããããã埮åãèªåã§å®è¡ããããšãææ¡ãããŠããŸãããããã¯ãããããããã¯ããã®ãããªè©³çŽ°ãªäŸãªãã§å€ãã®èšç®ã䌎ã次ã®èšäºã®ãããã¯ã«ãªãã§ãããã
ã±ãŒã¹ 2. ãªããžã§ã¯ãã®åé¡ Ðž
ããã§ã®ã¢ãããŒãã¯ã¯ã©ã¹ã®å Žåãšåãã§ã О ããã ããæ倱é¢æ°ã®åºåãžã®ãã¹èªäœã¯ ç©æµæ倱ãããè¯ããã«ãªããŸãã å§ããŸãããã 尀床é¢æ°ã«ã¯æŒç®åã䜿çšããŸãã ãããâŠã ã£ããâŠãã ã€ãŸãããã çªç®ã®ãªããžã§ã¯ãã¯ã¯ã©ã¹ã«å±ããŸã ã次ã«ããµã³ãã«ã®å°€åºŠãèšç®ããããã«ã確çã䜿çšããŸãã ããªããžã§ã¯ããã¯ã©ã¹ã«å±ããŠããå Žå ã確çã«ä»£å ¥ããŸãã ã 尀床é¢æ°ã¯æ¬¡ã®ããã«ãªããŸãã
ãããã©ã®ããã«æ©èœããããæã§èª¬æããŠã¿ãŸãããã 4 ã€ã®ã±ãŒã¹ãèããŠã¿ãŸãããã
1. ãã О ã®å Žåããµã³ããªã³ã°å°€åºŠã¯ãæžå°ãããŸãã
2. ãã О ã®å Žåããµã³ããªã³ã°å°€åºŠã¯ãæžå°ãããŸãã
3. ãã О ã®å Žåããµã³ããªã³ã°å°€åºŠã¯ãæžå°ãããŸãã
4. ãã О ã®å Žåããµã³ããªã³ã°å°€åºŠã¯ãæžå°ãããŸãã
ã±ãŒã¹ 1 ãš 3 ã§ã¯ã確çãã¢ã«ãŽãªãºã ã«ãã£ãŠæ£ãã決å®ãããå Žåã次ã®ããšãæããã§ãã 尀床é¢æ° ã€ãŸããããã¯ãŸãã«ç§ãã¡ãåŸããã£ããã®ã§ãã ãã ãããã®ã¢ãããŒãã¯éåžžã«é¢åãªã®ã§ã次ã«ãããã³ã³ãã¯ããªè¡šèšæ³ãæ€èšããŸãã ãã ããæåã«ã尀床é¢æ°ãæå°åããã®ã§ã笊å·ãå€æŽããŠå¯Ÿæ°èšç®ããŸãããã
代ããã«ä»£çšããŸããã è¡šçŸ :
åçŽãªç®è¡ææ³ã䜿çšããŠã察æ°ã®äžã®æ£ããé ãåçŽåãã次ãååŸããŸãããã
ä»åºŠã¯ãªãã¬ãŒã¿ãŒãæé€ããæãæ¥ãŸãã ãããâŠã ã£ããâŠãã ãªããžã§ã¯ãã ã¯ã©ã¹ã«å±ããŸã ã察æ°ã®äžã®åŒã§ãåæ¯ã§ã åãäžãã ããªããžã§ã¯ããã¯ã©ã¹ã«å±ããŠããå Žå ããã®åŸ $e$ ãã¹ãä¹ãããŸã ã ãããã£ãŠã床ã®è¡šèšã¯ãäž¡æ¹ã®ã±ãŒã¹ã XNUMX ã€ã«çµã¿åãããããšã§ç°¡ç¥åã§ããŸãã ã ãããã ããžã¹ãã£ãã¯èª€å·®é¢æ° 次ã®åœ¢åŒã«ãªããŸã:
察æ°ã®æ³åã«åŸã£ãŠãåæ°ãã²ã£ããè¿ããŠèšå·ãåºããŸãã" (ãã€ãã¹) 察æ°ã®å Žåã次ã®ããã«ãªããŸãã
ããã«æ倱é¢æ°ããããŸã ç©æµæ倱ãã¯ã©ã¹ã«ãªããžã§ã¯ããå²ãåœãŠããããã¬ãŒãã³ã° ã»ããã§äœ¿çšãããŸãã О .
ããŠããã®æç¹ã§äŒæãåãããã®èšäºãçµãããŸãã
è£å©ææ
1. æåŠ
1) å¿çšååž°åæ / N. DraperãG. Smith - 第 2 çâ M.: 財åãšçµ±èšã1986 (è±èªããã®ç¿»èš³)
2) 確çè«ãšæ°ççµ±èš / V.E. ã°ã ã«ãã³ - 第 9 ç- M.: é«çåŠæ ¡ã2003 幎
3) 確çè« / N.I. ãã§ã«ãã - ããã·ãã«ã¹ã¯: ããã·ãã«ã¹ã¯å·ç«å€§åŠã2007
4) ããžãã¹åæ: ããŒã¿ããç¥èãž / Paklin N. B.ãOreshkov V. I. - 第 2 çâ ãµã³ã¯ãããã«ãã«ã¯: ããŒã¿ãŒã2013
5) ããŒã¿ ãµã€ãšã³ã¹ ãŒãããã®ããŒã¿ ãµã€ãšã³ã¹ / Joel Gras - ãµã³ã¯ãããã«ãã«ã¯: BHV Petersburgã2017
6) ããŒã¿ ãµã€ãšã³ã¹ ã¹ãã·ã£ãªã¹ãã®ããã®å®è·µçµ±èš / P. ãã«ãŒã¹ãE. ãã«ãŒã¹ - ãµã³ã¯ãããã«ãã«ã¯: BHV Petersburgã2018
2. è¬æŒã»è¬åº§ïŒåç»ïŒ
1)
2)
3)
4)
5)
3. ã€ã³ã¿ãŒããããœãŒã¹
1)
2)
3)
4)
6)
8)
åºæïŒ habr.com