import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sklearn.linear_model06wk-24: 취업(다중공선성) / RidgeCV
1. 강의영상
2. Imports
3. Data
df = pd.read_csv("https://raw.githubusercontent.com/guebin/MP2023/main/posts/employment_multicollinearity.csv")
np.random.seed(43052)
df['employment_score'] = df.gpa * 1.0 + df.toeic* 1/100 + np.random.randn(500)df| employment_score | gpa | toeic | toeic0 | toeic1 | toeic2 | toeic3 | toeic4 | toeic5 | toeic6 | ... | toeic490 | toeic491 | toeic492 | toeic493 | toeic494 | toeic495 | toeic496 | toeic497 | toeic498 | toeic499 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1.784955 | 0.051535 | 135 | 129.566309 | 133.078481 | 121.678398 | 113.457366 | 133.564200 | 136.026566 | 141.793547 | ... | 132.014696 | 140.013265 | 135.575816 | 143.863346 | 152.162740 | 132.850033 | 115.956496 | 131.842126 | 125.090801 | 143.568527 |
| 1 | 10.789671 | 0.355496 | 935 | 940.563187 | 935.723570 | 939.190519 | 938.995672 | 945.376482 | 927.469901 | 952.424087 | ... | 942.251184 | 923.241548 | 939.924802 | 921.912261 | 953.250300 | 931.743615 | 940.205853 | 930.575825 | 941.530348 | 934.221055 |
| 2 | 8.221213 | 2.228435 | 485 | 493.671390 | 493.909118 | 475.500970 | 480.363752 | 478.868942 | 493.321602 | 490.059102 | ... | 484.438233 | 488.101275 | 485.626742 | 475.330715 | 485.147363 | 468.553780 | 486.870976 | 481.640957 | 499.340808 | 488.197332 |
| 3 | 2.137594 | 1.179701 | 65 | 62.272565 | 55.957257 | 68.521468 | 76.866765 | 51.436321 | 57.166824 | 67.834920 | ... | 67.653225 | 65.710588 | 64.146780 | 76.662194 | 66.837839 | 82.379018 | 69.174745 | 64.475993 | 52.647087 | 59.493275 |
| 4 | 8.650144 | 3.962356 | 445 | 449.280637 | 438.895582 | 433.598274 | 444.081141 | 437.005100 | 434.761142 | 443.135269 | ... | 455.940348 | 435.952854 | 441.521145 | 443.038886 | 433.118847 | 466.103355 | 430.056944 | 423.632873 | 446.973484 | 442.793633 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 495 | 9.057243 | 4.288465 | 280 | 276.680902 | 274.502675 | 277.868536 | 292.283300 | 277.476630 | 281.671647 | 296.307373 | ... | 269.541846 | 278.220546 | 278.484758 | 284.901284 | 272.451612 | 265.784490 | 275.795948 | 280.465992 | 268.528889 | 283.638470 |
| 496 | 4.108020 | 2.601212 | 310 | 296.940263 | 301.545000 | 306.725610 | 314.811407 | 311.935810 | 309.695838 | 301.979914 | ... | 304.680578 | 295.476836 | 316.582100 | 319.412132 | 312.984039 | 312.372112 | 312.106944 | 314.101927 | 309.409533 | 297.429968 |
| 497 | 2.430590 | 0.042323 | 225 | 206.793217 | 228.335345 | 222.115146 | 216.479498 | 227.469560 | 238.710310 | 233.797065 | ... | 233.469238 | 235.160919 | 228.517306 | 228.349646 | 224.153606 | 230.860484 | 218.683195 | 232.949484 | 236.951938 | 227.997629 |
| 498 | 5.343171 | 1.041416 | 320 | 327.461442 | 323.019899 | 329.589337 | 313.312233 | 315.645050 | 324.448247 | 314.271045 | ... | 326.297700 | 309.893822 | 312.873223 | 322.356584 | 319.332809 | 319.405283 | 324.021917 | 312.363694 | 318.493866 | 310.973930 |
| 499 | 6.505106 | 3.626883 | 375 | 370.966595 | 364.668477 | 371.853566 | 373.574930 | 376.701708 | 356.905085 | 354.584022 | ... | 382.278782 | 379.460816 | 371.031640 | 370.272639 | 375.618182 | 369.252740 | 376.925543 | 391.863103 | 368.735260 | 368.520844 |
500 rows × 503 columns
4. RidgeCV
- RidgeCV 클래스에서 모형을 선택해보자.
## step1
df_train, df_test = sklearn.model_selection.train_test_split(df,test_size=0.3,random_state=42)
X = df_train.loc[:,'gpa':'toeic499']
y = df_train.loc[:,'employment_score']
XX = df_test.loc[:,'gpa':'toeic499']
yy = df_test.loc[:,'employment_score']
## step2
predictr = sklearn.linear_model.RidgeCV()
## step3
predictr.fit(X,y)
## step4 -- pass RidgeCV()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RidgeCV()
predictr.score(X,y)0.9999996840224911predictr.score(XX,yy)0.1191494594976158- alpha들의 후보를 우리가 직접 선정하자.
## step1
df_train, df_test = sklearn.model_selection.train_test_split(df,test_size=0.3,random_state=42)
X = df_train.loc[:,'gpa':'toeic499']
y = df_train.loc[:,'employment_score']
XX = df_test.loc[:,'gpa':'toeic499']
yy = df_test.loc[:,'employment_score']
## step2
predictr = sklearn.linear_model.RidgeCV(alphas=[5e2, 5e3, 5e4, 5e5, 5e6, 5e7, 5e8])
## step3
predictr.fit(X,y)
## step4 -- pass RidgeCV(alphas=[500.0, 5000.0, 50000.0, 500000.0, 5000000.0, 50000000.0,
500000000.0])In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RidgeCV(alphas=[500.0, 5000.0, 50000.0, 500000.0, 5000000.0, 50000000.0,
500000000.0])predictr.score(X,y)0.7521268560159359predictr.score(XX,yy)0.7450309251010895predictr.alpha_50000000.0참고로 이 적합결과는 아래의 코드를 실행한것과 같다
## step1
df_train, df_test = sklearn.model_selection.train_test_split(df,test_size=0.3,random_state=42)
X = df_train.loc[:,'gpa':'toeic499']
y = df_train.loc[:,'employment_score']
XX = df_test.loc[:,'gpa':'toeic499']
yy = df_test.loc[:,'employment_score']
## step2
predictr = sklearn.linear_model.Ridge(alpha=50000000.0)
## step3
predictr.fit(X,y)
## step4 -- pass Ridge(alpha=50000000.0)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Ridge(alpha=50000000.0)
predictr.score(X,y)0.752126856015936predictr.score(XX,yy)0.7450309251010895