Improve RF and fix requirements.txt

shalinis602 · Jul 12, 2024 · 72c7c39 · 72c7c39
1 parent b4539dc
commit 72c7c39
Show file tree

Hide file tree

Showing 8 changed files with 573 additions and 412 deletions.
diff --git a/.ipynb_checkpoints/rna-seq-ml-modeling-checkpoint.ipynb b/.ipynb_checkpoints/rna-seq-ml-modeling-checkpoint.ipynb
diff --git a/data/processed/transformed/explained_variance_plot.png b/data/processed/transformed/explained_variance_plot.png
diff --git a/requirements.txt b/requirements.txt
diff --git a/results/pre_processing/explained_variance_plot.png b/results/pre_processing/explained_variance_plot.png
diff --git a/results/pre_processing/pca.txt b/results/pre_processing/pca.txt
@@ -0,0 +1,17 @@
+Explained variance ratios for each component:
+Principal Component 1: 0.1394
+Principal Component 2: 0.1006
+Principal Component 3: 0.0764
+Principal Component 4: 0.0596
+Principal Component 5: 0.0391
+Principal Component 6: 0.0321
+Principal Component 7: 0.0222
+
+Cumulative explained variance ratios:
+Principal Component 1: 0.1394
+Principal Component 2: 0.2400
+Principal Component 3: 0.3164
+Principal Component 4: 0.3760
+Principal Component 5: 0.4151
+Principal Component 6: 0.4472
+Principal Component 7: 0.4694
diff --git a/results/random_forest.txt b/results/random_forest.txt
@@ -1,41 +1,41 @@
-Validation Accuracy: 0.22
+Validation Accuracy: 0.96
 Validation Classification Report:
               precision    recall  f1-score   support
 
-        BRCA       0.17      0.04      0.06        28
-        COAD       0.00      0.00      0.00         9
-        KIRC       0.00      0.00      0.00        10
-        LUAD       0.00      0.00      0.00        13
-        PRAD       0.89      0.81      0.85        21
+        BRCA       0.93      1.00      0.97        28
+        COAD       1.00      1.00      1.00         9
+        KIRC       1.00      0.90      0.95        10
+        LUAD       0.92      0.92      0.92        13
+        PRAD       1.00      0.95      0.98        21
 
-    accuracy                           0.22        81
-   macro avg       0.21      0.17      0.18        81
-weighted avg       0.29      0.22      0.24        81
+    accuracy                           0.96        81
+   macro avg       0.97      0.96      0.96        81
+weighted avg       0.96      0.96      0.96        81
 
 Validation Confusion Matrix:
-[[ 1 19  3  3  2]
- [ 0  0  9  0  0]
- [ 0  5  0  5  0]
- [ 1  5  7  0  0]
- [ 4  0  0  0 17]]
+[[28  0  0  0  0]
+ [ 0  9  0  0  0]
+ [ 0  0  9  1  0]
+ [ 1  0  0 12  0]
+ [ 1  0  0  0 20]]
 
-Test Accuracy: 0.12
+Test Accuracy: 0.99
 Test Classification Report:
               precision    recall  f1-score   support
 
-        BRCA       0.00      0.00      0.00        27
-        COAD       0.00      0.00      0.00         8
-        KIRC       0.00      0.00      0.00        15
-        LUAD       0.00      0.00      0.00        19
-        PRAD       0.62      0.91      0.74        11
+        BRCA       1.00      0.96      0.98        27
+        COAD       1.00      1.00      1.00         8
+        KIRC       1.00      1.00      1.00        15
+        LUAD       0.95      1.00      0.97        19
+        PRAD       1.00      1.00      1.00        11
 
-    accuracy                           0.12        80
-   macro avg       0.12      0.18      0.15        80
-weighted avg       0.09      0.12      0.10        80
+    accuracy                           0.99        80
+   macro avg       0.99      0.99      0.99        80
+weighted avg       0.99      0.99      0.99        80
 
 Test Confusion Matrix:
-[[ 0 17  3  1  6]
- [ 0  0  8  0  0]
- [ 2  2  0 11  0]
- [ 3  4 12  0  0]
- [ 1  0  0  0 10]]
+[[26  0  0  1  0]
+ [ 0  8  0  0  0]
+ [ 0  0 15  0  0]
+ [ 0  0  0 19  0]
+ [ 0  0  0  0 11]]
diff --git a/rna-seq-ml-modeling.ipynb b/rna-seq-ml-modeling.ipynb
@@ -228,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "6797f2bc",
    "metadata": {},
    "outputs": [
@@ -254,7 +254,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 6,
    "id": "8f59d610",
    "metadata": {},
    "outputs": [
@@ -348,7 +348,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "id": "4c88dfb4",
    "metadata": {},
    "outputs": [
@@ -514,7 +514,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d1e3b956",
+   "id": "b26ed2f6",
    "metadata": {},
    "outputs": [],
    "source": []

diff --git a/src/pca.py b/src/pca.py
@@ -61,18 +61,22 @@ def main():
     plt.legend(loc='best')
     plt.grid(True)
 
-    plot_filename = os.path.join(output_dir, 'explained_variance_plot.png')
+    output_dir2 = 'results/pre_processing'
+    os.makedirs(output_dir2, exist_ok=True)
+    plot_filename = os.path.join(output_dir2, 'explained_variance_plot.png')
     plt.savefig(plot_filename)
     plt.show()
 
-    # Print explained variance values for the selected components
-    print("Explained variance ratios for each component:")
-    for i, var in enumerate(explained_variance, start=1):
-        print(f"Principal Component {i}: {var:.4f}")
+    # Save explained variance values for the selected components
+    pca_file_path = os.path.join(output_dir2, 'pca.txt')
+    with open(pca_file_path, "w") as f:
+        f.write("Explained variance ratios for each component:\n")
+        for i, var in enumerate(explained_variance, start=1):
+            f.write(f"Principal Component {i}: {var:.4f}\n")
 
-    print("\nCumulative explained variance ratios:")
-    for i, cum_var in enumerate(cumulative_explained_variance, start=1):
-        print(f"Principal Component {i}: {cum_var:.4f}")
+        f.write("\nCumulative explained variance ratios:\n")
+        for i, cum_var in enumerate(cumulative_explained_variance, start=1):
+            f.write(f"Principal Component {i}: {cum_var:.4f}\n")
 
 if __name__ == "__main__":
     main()