diff --git a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.Rmd b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.Rmd index e41bf22..c329ed9 100644 --- a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.Rmd +++ b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.Rmd @@ -3,14 +3,14 @@ title: 'CTBench Eval Project Notebook:' author: "Your Name Here" date: "`r format(Sys.time(), '%d %B %Y')`" output: - pdf_document: - toc: true - number_sections: true - fig_caption: false html_document: toc: true number_sections: true df_print: paged + pdf_document: + toc: true + number_sections: true + fig_caption: false subtitle: DAR Assignment 3 (Fall 2024) --- ```{r setup, include=FALSE} diff --git a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.html b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.html index 753e91a..f80395b 100644 --- a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.html +++ b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.html @@ -2179,14 +2179,16 @@

5.1 How do results differ Differences by Model on CT-Pub - - - + + + + +model meanPrecision sePrecision meanRecall @@ -2197,12 +2199,40 @@

5.1 How do results differ -0.4344882 -0.0084623 -0.5272768 -0.0104531 -0.4517983 -0.0072764 +gpt4-omni-ts +0.4194773 +0.0165780 +0.5465613 +0.0206740 +0.4519953 +0.0145372 + + +gpt4-omni-zs +0.4117923 +0.0191232 +0.4988831 +0.0196749 +0.4250843 +0.0150289 + + +llama3-70b-in-ts +0.4372443 +0.0146389 +0.5267929 +0.0209162 +0.4550647 +0.0137912 + + +llama3-70b-in-zs +0.4694388 +0.0167251 +0.5368701 +0.0222861 +0.4750490 +0.0146080 @@ -2227,21 +2257,26 @@

5.2 How do results differ meanRecall=mean(recall), seRecall=std.error(recall), meanF1=mean(f1), - sef1=std.error(f1)) - -kable(CT_Pub_MT_results.df, caption="Differences by Model and Subgroup on CT-pub") + sef1=std.error(f1)) +
## `summarise()` has grouped output by 'model'. You can override using the
+## `.groups` argument.
+
kable(CT_Pub_MT_results.df, caption="Differences by Model and Subgroup on CT-pub")
------++++++++ + + @@ -2252,12 +2287,204 @@

5.2 How do results differ

- - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Differences by Model and Subgroup on CT-pub
modeltrial_group meanPrecision sePrecision meanRecall
0.43448820.00846230.52727680.01045310.45179830.0072764gpt4-omni-tscancer0.33763330.03994970.54308990.03928550.39708810.0344699
gpt4-omni-tschronic kidney disease0.44300210.03035950.56253530.05182430.47892170.0327797
gpt4-omni-tsdiabetes0.43150310.02611830.59845200.03637880.48151790.0242987
gpt4-omni-tshypertension0.49368920.04216460.50763530.05706180.47088210.0340076
gpt4-omni-tsobesity0.38826680.04951000.46593320.04874580.40342060.0390612
gpt4-omni-zscancer0.35938960.06486990.51772480.03782280.38848220.0416444
gpt4-omni-zschronic kidney disease0.44982550.03591250.49617750.04221650.45505350.0337143
gpt4-omni-zsdiabetes0.43988740.02751780.56701200.03502870.47474530.0243584
gpt4-omni-zshypertension0.41104570.05257730.44042360.05248250.39163990.0329269
gpt4-omni-zsobesity0.36785170.04889320.40162090.04727450.35985840.0359429
llama3-70b-in-tscancer0.40937690.03214810.56665990.04833300.45196190.0284682
llama3-70b-in-tschronic kidney disease0.45383990.03677680.51582420.05688430.45916010.0350896
llama3-70b-in-tsdiabetes0.45710220.02480110.57087320.03432730.48623240.0235926
llama3-70b-in-tshypertension0.49835490.03700430.48183630.05994630.46579950.0376744
llama3-70b-in-tsobesity0.36037990.03288180.45402760.04379460.38650560.0317837
llama3-70b-in-zscancer0.41385440.04147520.63229740.04928220.48364210.0366250
llama3-70b-in-zschronic kidney disease0.52659880.04327490.57016150.06373680.50700080.0362418
llama3-70b-in-zsdiabetes0.49250060.02550360.53531390.03507230.49802890.0246477
llama3-70b-in-zshypertension0.50758600.04882540.51096070.06308180.47579890.0373848
llama3-70b-in-zsobesity0.38845610.03406090.44184560.04605360.39146920.0307577
diff --git a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.pdf b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.pdf index 0a3c8d4..a67bb65 100644 Binary files a/StudentNotebooks/Assignment03/dar-f24-assignment3-template.pdf and b/StudentNotebooks/Assignment03/dar-f24-assignment3-template.pdf differ