ð©âðçŸåœ¹ããã°ã©ããŒã«ããæ°åéžæåŒå®ããAIäºæ³ãµã€ãðchatGPTã䜿ã£ã什åææ°ã®ããžãã¹ã¢ãã«ðææ°ããŒã¿ãchatGPTã«æäŸãåºåð±Pythonã«ããæ©æ¢°åŠç¿ãšã®AIã³ã©ãã¬ãŒã·ã§ã³ð¯äººå·¥ç¥èœã§åœéžã§ããæ代ã«çªå ¥ðnoteã§é«ãçäžçãç®æãæå 端ã®AIäºæ³ãµã€ãð¯
ð©âðçŸåœ¹ããã°ã©ããŒ6人è¡ã§éå¶
ð¯çŸåœ¹ããã°ã©ããŒå€©æé幎ðŽèµ€
ð¯çŸåœ¹ããã°ã©ããŒå€©æå°å¥³ðµé
ð¯çŸåœ¹ããã°ã©ããŒå€©æå士â«é»
ð¯çŸåœ¹ããã°ã©ããŒå€©æææð¡é»
ð¯çŸåœ¹ããã°ã©ããŒå€©ææš©åšð¢ç·
ð¯çŸåœ¹ããã°ã©ããŒå€©æåŠè
ð£çŽ«
â»äºæ³æ°åã¯å šãŠåãã§ã¯ãããŸããã
ð©âðçŸåœ¹ããã°ã©ããŒã«ããæ°åéžæåŒå®ããã®AIäºæ³ãµã€ã
ð©âðchatGPTã䜿ã£ã什åææ°ã®ããžãã¹ã¢ãã«
ð©âðææ°ããŒã¿ãchatGPTã«æäŸãåºå
ð©âðPythonã«ããæ©æ¢°åŠç¿ãšã®AIã³ã©ãã¬ãŒã·ã§ã³
ð©âð人工ç¥èœã§åœéžã§ããæ代ã«çªå
¥
ð©âðnoteã§é«ãçäžçãç®æãæå
端ã®AIäºæ³ãµã€ã
ð©âðæœéžåŸã®22æãŸã§ã«è§£æã次ååœéžäºæ³æ°åãå
Ž
æææ¥ïŒð¥ãã³ããŒãº3ðŠãã³ããŒãº4ðªãã6
ç«ææ¥ïŒð¥ãã³ããŒãº3ðŠãã³ããŒãº4ð«ãããã
æ°Žææ¥ïŒð¥ãã³ããŒãº3ðŠãã³ããŒãº4
æšææ¥ïŒð¥ãã³ããŒãº3ðŠãã³ããŒãº4ðªãã6
éææ¥ïŒð¥ãã³ããŒãº3ðŠãã³ããŒãº4ðšãã7
ðã©ãã ã説æããŠãå®çžŸãå
šãŠã®äžçãªã®ã¯çŸãæ¿ç¥ã§ãã®ã§ã以äžåœéžå®çžŸããªã³ã¯ä»ãã§èŒããŸãã
ðš24幎04æäºæ³çäžçµæð¯åœéžããã§ãšãããããŸãð
ð¯ç¬¬6455å2024幎04æ25æ¥(æš)ð¥ãã³ããŒãº3ããã¯ã¹ð¯13,300å
ð¯ç¬¬6452å2024幎04æ22æ¥(æ)ð¥ãã³ããŒãº3ã¹ãã¬ãŒãð¯88,300å
ð¯ç¬¬6450å2024幎04æ18æ¥(æš)ðŠãã³ããŒãº4ããã¯ã¹ð¯27,700å
ð¯ç¬¬6449å2024幎04æ17æ¥(æ°Ž)ð¥ãã³ããŒãº3ããã¯ã¹ð¯12,900å
ð¯ç¬¬6445å2024幎04æ11æ¥(æ°Ž)ðŠãã³ããŒãº4ã¹ãã¬ãŒãð¯599,500å
ð¯ç¬¬6442å2024幎04æ08æ¥(æ)ðŠãã³ããŒãº4ããã¯ã¹ð¯32,300å
ð¯ç¬¬0569å2024幎04æ05æ¥(é)ðšãã7 5çð¯1,500å
ð¯ç¬¬6437å2024幎04æ01æ¥(æ)ðŠãã³ããŒãº4ããã¯ã¹ð¯17,500å
ðš24幎03æäºæ³çäžçµæð¯åœéžããã§ãšãããããŸãð
ð¯ç¬¬6433å2024幎03æ26æ¥(ç«)ð¥ãã³ããŒãº3ããã¯ã¹ð¯14,100å
ð¯ç¬¬1881å2024幎03æ25æ¥(æ)ðªãã6 4çð¯8,700å
ð¯ç¬¬6430å2024幎03æ21æ¥(æš)ðŠãã³ããŒãº4ããã¯ã¹ð¯71,900å
ð¯ç¬¬6427å2024幎03æ18æ¥(æ)ð¥ãã³ããŒãº3ããã¯ã¹ð¯9,400å
ð¯ç¬¬6423å2024幎03æ12æ¥(ç«)ðŠãã³ããŒãº4ã¹ãã¬ãŒãð¯804,300å
ð¯ç¬¬6418å2024幎03æ05æ¥(ç«)ð¥ãã³ããŒãº3ã¹ãã¬ãŒãð¯147,300å
ð¯ç¬¬6417å2024幎03æ04æ¥(æ)ðŠãã³ããŒãº4ããã¯ã¹ð¯44,400å
ðš24幎02æäºæ³çäžçµæð¯åœéžããã§ãšãããããŸãð
ð¯ç¬¬6415å2024幎02æ29æ¥(æš)ðŠãã³ããŒãº4ããã¯ã¹ð¯124,000å
ð¯ç¬¬1272å2024幎02æ27æ¥(ç«)ð«ãããã 4çð¯900å
ð¯ç¬¬1872å2024幎02æ22æ¥(æš)ðªãã6 5çð¯1,000å
ð¯ç¬¬6407å2024幎02æ19æ¥(æ)ð¥ãã³ããŒãº3ããã¯ã¹ð¯15,000å
ð¯ç¬¬6405å2024幎02æ15æ¥(æš)ðŠãã³ããŒãº4ããã¯ã¹ð¯28,100å
ð¯ç¬¬6401å2024幎02æ09æ¥(é)ðŠãã³ããŒãº4ããã¯ã¹ð¯43,300å
ð¯ç¬¬6397å2024幎02æ05æ¥(æ)ðŠãã³ããŒãº4ããã¯ã¹ð¯35,100å
ð¯ç¬¬6395å2024幎02æ01æ¥(æš)ð¥ãã³ããŒãº3ã¹ãã¬ãŒãð¯58,900å
ðš24幎01æäºæ³çäžçµæð¯åœéžããã§ãšãããããŸãð
ð¯ç¬¬6392å2024幎01æ29æ¥(æ)ðŠãã³ããŒãº4ã¹ãã¬ãŒãð¯874,300å
ð¯ç¬¬6389å2024幎01æ24æ¥(æ°Ž)ð¥ãã³ããŒãº3ããã¯ã¹ð¯11,400å
ð¯ç¬¬6387å2024幎01æ22æ¥(æ)ðŠãã³ããŒãº4ããã¯ã¹ð¯44,800å
ð¯ç¬¬0558å2024幎01æ19æ¥(é)ðšãã7 5çð¯1,600å
ð¯ç¬¬6384å2024幎01æ17æ¥(æ°Ž)ð¥ãã³ããŒãº3ã¹ãã¬ãŒãð¯92,500å
ð¯ç¬¬6379å2024幎01æ10æ¥(æ°Ž)ð¥ãã³ããŒãº3ããã¯ã¹ð¯17,200å
ð¯ç¬¬1859å2024幎01æ08æ¥(æ)ðªãã6 4çð¯6,500å
â ChatGPTãšã¯é«åºŠãªAIæè¡ã«ãã£ãŠOpenAI瀟ãéçºãã人工ç¥èœåã®ããã°ã©ã ã
ChatGPTãšã¯é«åºŠãªAIæè¡ã«ãã£ãŠOpenAI瀟ãéçºãã人工ç¥èœåã®ããã°ã©ã ã§ãã
â ãã³ããŒãºã®ãµã³ãã«ããã°ã©ã å ¬é
éå»ã®ããã°ããŒã¿ããæœéžçµæã«åºã¥ã解æãšæœåºèšå®ãããŠããŸããããããèšå®ããããšã§ããå¹çããåœéžæ°åãçµã蟌ãããšãåºæ¥ãŸãã
# ã¡ã€ã³é¢æ°
def run():
# ãã¡ã€ã«èªã¿èŸŒã¿
df = pd.read_csv("./input/Numbers3.csv", header=1, encoding="shift_jis")
# ããŒã¿ãã¬ãŒã å
num_cols = ['ã¹ãã¬ãŒãå£æ°', 'ã¹ãã¬ãŒãéé¡', 'ããã¯ã¹å£æ°', 'ããã¯ã¹éé¡', 'ã»ããã¹ãã¬ãŒãå£æ°',
'ã»ããã¹ãã¬ãŒãéé¡', 'ã»ããããã¯ã¹å£æ°', 'ã»ããããã¯ã¹éé¡', 'ããå£æ°', 'ããéé¡']
for col in num_cols:
df[col] = df[col].str.replace(",", "")
df[num_cols] = df[num_cols].astype(float)
# åœéžçªå·ãæååå
df['åœããçªå·_æåå'] = df['åœããçªå·'].astype(str)
# åœéžçªå·ã0åã
df['åœããçªå·_æåå'] = df['åœããçªå·_æåå'].str.zfill(3)
# åœéžçªå·ã®åæ¡ãæœåº
df['åœããçªå·_çŸ'] = df['åœããçªå·_æåå'].str[0].astype(int)
df['åœããçªå·_å'] = df['åœããçªå·_æåå'].str[1].astype(int)
df['åœããçªå·_äž'] = df['åœããçªå·_æåå'].str[2].astype(int)
# å¶æ°å¥æ°å€å®
df['åœããçªå·_å¶å¥å€å®'] = df['åœããçªå·'].apply(lambda x: even_odd_check(x))
df['åœããçªå·_çŸ_å¶å¥å€å®'] = df['åœããçªå·_çŸ'].apply(lambda x: even_odd_check(x))
df['åœããçªå·_å_å¶å¥å€å®'] = df['åœããçªå·_å'].apply(lambda x: even_odd_check(x))
df['åœããçªå·_äž_å¶å¥å€å®'] = df['åœããçªå·_äž'].apply(lambda x: even_odd_check(x))
# 3æ¡ã®æ°åã®åèš
df['åœããçªå·_3æ¡ã®åèš'] = df['åœããçªå·_çŸ'] + df['åœããçªå·_å'] + df['åœããçªå·_äž']
# éé ã«ããè¡ãç¹°ãè¿ãåŠç
_list = []
reverse_df = df.iloc[::-1].reset_index(drop=True)
# foræå
ã§äœ¿ãå€æ°ã®æºå
digits = ['çŸ', 'å', 'äž']
past_numbers = [0, 0, 0]
continuous_times = [0, 0, 0]
for i, row in tqdm(reverse_df.iterrows(), total=len(df)):
_dict = {}
# åæ¡ã®å¶æ°/å¥æ°ã®çµã¿åãããå€å®
if (row['åœããçªå·_çŸ_å¶å¥å€å®'] == "odd") & (row['åœããçªå·_å_å¶å¥å€å®'] == "odd") & (
row['åœããçªå·_äž_å¶å¥å€å®'] == "odd"):
# å
šãŠå¥æ°
_dict['åœããçªå·_åæ¡å¶å¥å€å®'] = 'all_odd'
elif (row['åœããçªå·_çŸ_å¶å¥å€å®'] == "even") & (row['åœããçªå·_å_å¶å¥å€å®'] == "even") & (
row['åœããçªå·_äž_å¶å¥å€å®'] == "even"):
# å
šãŠå¶æ°
_dict['åœããçªå·_åæ¡å¶å¥å€å®'] = 'all_even'
else:
# å¥æ°ãšå¶æ°ãæ··åš
_dict['åœããçªå·_åæ¡å¶å¥å€å®'] = 'mix_odd_even'
# åæ¡ãé£ç¶ã§åäžããå€å®
for j, digit in enumerate(digits):
if i != 0: # ååã¯å®è¡ããªã
if past_numbers[j] == row[f'åœããçªå·_{digit}']:
# ååã®æ°å€ãšäžèŽããå Žåãé£ç¶åºçŸåæ°ãã€ã³ã¯ãªã¡ã³ã
continuous_times[j] += 1
_dict[f'é£ç¶åºçŸåæ°_{digit}'] = continuous_times[j]
else:
# ååã®æ°å€ãšäžèŽããªãå Žåãé£ç¶åºçŸåæ°ããªã»ãã
continuous_times[j] = 0
_dict[f'é£ç¶åºçŸåæ°_{digit}'] = continuous_times[j]
# 次ã®è¡ã§äœ¿çšããããã«çŸåšã®æ°å€ãæ ŒçŽ
past_numbers[j] = row[f'åœããçªå·_{digit}']
else:
# åæå€ãèšå®
_dict[f'é£ç¶åºçŸåæ°_{digit}'] = continuous_times[j]
# 次ã®è¡ã§äœ¿çšããããã«çŸåšã®æ°å€ãæ ŒçŽ
past_numbers[j] = row[f'åœããçªå·_{digit}']
# ããŒã¿ãã¬ãŒã ã®1è¡ã«ãããèŸæžããªã¹ãã«è¿œå
_list.append(_dict)
# ãªã¹ããããŒã¿ãã¬ãŒã åããŠãå
ã®ããŒã¿ãã¬ãŒã ãšé£çµ
_df = pd.DataFrame(_list)
concat_df = pd.concat([reverse_df, _df], axis=1)
# ããŒã¿ãã¬ãŒã ã®é åºãå
ã«æ»ããŠä¿å
result_df = concat_df.iloc[::-1].reset_index(drop=True)
result_df.to_csv('output/result.csv', index=False, encoding="shift-jis")
if __name__ == '__main__':
run()
ðµãã³ããŒãºïŒã®å¥æ°å¶æ°ã®æ¯ãåãâ0åã»ã»ã»20%以äžâ1åã»ã»ã»35%以äžâ2åã»ã»ã»30%以äžâ3åã»ã»ã»10%以äžâ4åã»ã»ã»5%以äžâ¡å
šäœã®85ïŒ
çšåºŠãå ãã0~2åãèšå®ããŠããŸã
ðšåœãµã€ãã®åœéžæ°åæœåºã«ã€ããŸããŠã¯åœéžãä¿èšŒãããã®ã§ã¯ãããŸããã®ã§èªå·±è²¬ä»»ã§ãå©çšããã ããŸããããé¡ãããŸãã
#å¯æ¥
#æè³
#ã®ã£ã³ãã«
#äºæ³
#転è·
#ãããããžãã¹
#å®ãã
#AI
#人工ç¥èœ
#æ°åéžæåŒå®ãã
#ãéã皌ã
#ãã³ããŒãº3
#ãã³ããŒãº3ãã
#ãã³ããŒãº4
#NUMBERS3
#NUMBERS4
#Python
#ãã³ããŒãº3äºæ³
#ãã³ããŒãºäºæ³
#ãã³ãŽ5
#ãã³ãŽ5äºæ³
#ãã6
#ãã6äºæ³
#ãã7
#ãã7äºæ³
#ãããã
#ããããäºæ³
#ãã£ããGPT
#chatGPT
#AIãã£ãã
ãã®èšäºãæ°ã«å ¥ã£ãããµããŒããããŠã¿ãŸãããïŒ