added lab 4

2025-10-31 17:55:13 -04:00
parent dc2ceac7de
commit 88f2975b86
66 changed files with 730 additions and 301 deletions
@@ -0,0 +1,62 @@
+{
+  "data": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/epi_results_2024_pop_gdp_v2.csv",
+  "region_col": "region",
+  "response": "EPI.new",
+  "region_a": "Sub-Saharan Africa",
+  "region_b": "Latin America & Caribbean",
+  "predictors": [
+    "gdp",
+    ["gdp", "population"]
+  ],
+  "knn1": ["AGR.new", "AIR.new", "APO.new"],
+  "knn2": ["BCA.new", "BDH.new", "CBP.new"],
+  "k": 5,
+  "fig_dir": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures",
+  "stats_dir": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/stats",
+  "box_a": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/box_Sub-Saharan_Africa_EPI.new.png",
+  "box_b": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/box_Latin_America_Caribbean_EPI.new.png",
+  "hist_a": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/hist_Sub-Saharan_Africa_EPI.new.png",
+  "hist_b": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/hist_Latin_America_Caribbean_EPI.new.png",
+  "qq_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/qq_EPI.new_Sub-Saharan_Africa_vs_Latin_America_Caribbean.png",
+  "ols": [
+    {
+      "name": "full: EPI.new ~ gdp",
+      "rsq": 0.5224,
+      "aic": 1257.4369,
+      "bic": 1266.999,
+      "nobs": 179,
+      "summary_file": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/stats/ols_full_EPI.new_gdp.txt",
+      "residuals_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/residuals_full_EPI.new_gdp.png",
+      "scatter_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/scatter_full_EPI.new_gdp_gdp.png"
+    },
+    {
+      "name": "full: EPI.new ~ gdp + population",
+      "rsq": 0.5392,
+      "aic": 1246.1592,
+      "bic": 1258.8864,
+      "nobs": 178,
+      "summary_file": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/stats/ols_full_EPI.new_gdp_population.txt",
+      "residuals_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/residuals_full_EPI.new_gdp_population.png",
+      "scatter_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/scatter_full_EPI.new_gdp_population_gdp.png"
+    }
+  ],
+  "best_region_note": "on region `Sub-Saharan Africa`, the better model is **region Sub-Saharan Africa: EPI.new ~ gdp + population** (r²=0.361, aic=265.4, bic=272.7).",
+  "knn": [
+    {
+      "tag": "model A",
+      "k": 5,
+      "vars": ["AGR.new", "AIR.new", "APO.new"],
+      "accuracy": 0.5581,
+      "confusion_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/knn_confusion_model_A.png",
+      "n_test": 43
+    },
+    {
+      "tag": "model B",
+      "k": 5,
+      "vars": ["BCA.new", "BDH.new", "CBP.new"],
+      "accuracy": 0.5116,
+      "confusion_fig": "/home/ion606/Desktop/Homework/Data Analytics/Assignments/Assignment II/output/figures/knn_confusion_model_B.png",
+      "n_test": 43
+    }
+  ]
+}