Spaces:
Sleeping
Sleeping
Shebsheb
Browse files- GNB/Variance_threshhold_code_preprocessing.py +38 -0
- GNB/__pycache__/gaussian_naive_bayes.cpython-312.pyc +0 -0
- GNB/__pycache__/gaussian_naive_bayes.cpython-313.pyc +0 -0
- gaussian_naive_bayes.py → GNB/gaussian_naive_bayes.py +0 -0
- GNB/naive_bayes_binary_full_preprocessing.py +174 -0
- GNB/pca+VT+NAIVE_MODEL_mutli.py +179 -0
- app.py +1 -1
GNB/Variance_threshhold_code_preprocessing.py
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
# Load dataset
|
| 5 |
+
import keras
|
| 6 |
+
(X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data(path="mnist.npz")
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
# Flatten images: (60000, 28, 28) → (60000, 784)
|
| 10 |
+
X_train = X_train.reshape(X_train.shape[0], -1)
|
| 11 |
+
X_test = X_test.reshape(X_test.shape[0], -1)
|
| 12 |
+
|
| 13 |
+
# Normalize (important for variance stability)
|
| 14 |
+
X_train = X_train / 255.0
|
| 15 |
+
X_test = X_test / 255.0
|
| 16 |
+
def compute_pixel_variance(X):
|
| 17 |
+
mean = np.mean(X, axis=0)
|
| 18 |
+
variance = np.mean((X - mean) ** 2, axis=0)
|
| 19 |
+
return variance
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
def variance_threshold(X, threshold=1e-4):
|
| 23 |
+
variances = compute_pixel_variance(X)
|
| 24 |
+
mask = variances > threshold
|
| 25 |
+
X_reduced = X[:, mask]
|
| 26 |
+
return X_reduced, mask, variances
|
| 27 |
+
# Apply your method
|
| 28 |
+
X_reduced, mask, variances = variance_threshold(X_train, threshold=1e-4)
|
| 29 |
+
|
| 30 |
+
# Print results
|
| 31 |
+
original_features = X_train.shape[1]
|
| 32 |
+
remaining_features = X_reduced.shape[1]
|
| 33 |
+
removed_features = original_features - remaining_features
|
| 34 |
+
|
| 35 |
+
print(f"Original pixels: {original_features}")
|
| 36 |
+
print(f"Remaining pixels: {remaining_features}")
|
| 37 |
+
print(f"Removed pixels: {removed_features}")
|
| 38 |
+
print(f"Reduction: {removed_features/original_features * 100:.2f}%")
|
GNB/__pycache__/gaussian_naive_bayes.cpython-312.pyc
ADDED
|
Binary file (1.99 kB). View file
|
|
|
GNB/__pycache__/gaussian_naive_bayes.cpython-313.pyc
ADDED
|
Binary file (2.07 kB). View file
|
|
|
gaussian_naive_bayes.py → GNB/gaussian_naive_bayes.py
RENAMED
|
File without changes
|
GNB/naive_bayes_binary_full_preprocessing.py
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
import matplotlib.pyplot as plt
|
| 3 |
+
import seaborn as sns
|
| 4 |
+
import keras
|
| 5 |
+
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
|
| 6 |
+
from DT.DecisionTree import DecisionTree
|
| 7 |
+
|
| 8 |
+
# ======================
|
| 9 |
+
# 1. LOAD DATA
|
| 10 |
+
# ======================
|
| 11 |
+
(X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data()
|
| 12 |
+
|
| 13 |
+
# Flatten
|
| 14 |
+
X_train = X_train.reshape(X_train.shape[0], -1)
|
| 15 |
+
X_test = X_test.reshape(X_test.shape[0], -1)
|
| 16 |
+
|
| 17 |
+
# Normalize
|
| 18 |
+
X_train = X_train / 255.0
|
| 19 |
+
X_test = X_test / 255.0
|
| 20 |
+
|
| 21 |
+
# ======================
|
| 22 |
+
# 2. BINARY LABELS (6 vs NOT 6)
|
| 23 |
+
# ======================
|
| 24 |
+
y_train_bin = (y_train == 6).astype(int)
|
| 25 |
+
y_test_bin = (y_test == 6).astype(int)
|
| 26 |
+
|
| 27 |
+
# ======================
|
| 28 |
+
# 3. VARIANCE FILTER
|
| 29 |
+
# ======================
|
| 30 |
+
def compute_pixel_variance(X):
|
| 31 |
+
mean = np.mean(X, axis=0)
|
| 32 |
+
return np.mean((X - mean) ** 2, axis=0)
|
| 33 |
+
|
| 34 |
+
def variance_threshold(X, threshold=1e-4):
|
| 35 |
+
variances = compute_pixel_variance(X)
|
| 36 |
+
mask = variances > threshold
|
| 37 |
+
return X[:, mask], mask
|
| 38 |
+
|
| 39 |
+
X_train_clean, mask = variance_threshold(X_train)
|
| 40 |
+
X_test_clean = X_test[:, mask]
|
| 41 |
+
|
| 42 |
+
print("After variance filtering:", X_train_clean.shape)
|
| 43 |
+
|
| 44 |
+
# ======================
|
| 45 |
+
# 4. BALANCE DATA (UNDERSAMPLING)
|
| 46 |
+
# ======================
|
| 47 |
+
def balance_data(X, y):
|
| 48 |
+
idx_6 = np.where(y == 1)[0]
|
| 49 |
+
idx_not6 = np.where(y == 0)[0]
|
| 50 |
+
|
| 51 |
+
np.random.shuffle(idx_not6)
|
| 52 |
+
idx_not6 = idx_not6[:len(idx_6)]
|
| 53 |
+
|
| 54 |
+
idx_balanced = np.concatenate([idx_6, idx_not6])
|
| 55 |
+
np.random.shuffle(idx_balanced)
|
| 56 |
+
|
| 57 |
+
return X[idx_balanced], y[idx_balanced]
|
| 58 |
+
|
| 59 |
+
X_train_bal, y_train_bal = balance_data(X_train_clean, y_train_bin)
|
| 60 |
+
|
| 61 |
+
print("Balanced shape:", X_train_bal.shape)
|
| 62 |
+
print("Class counts:", np.bincount(y_train_bal))
|
| 63 |
+
|
| 64 |
+
# ======================
|
| 65 |
+
# 5. PCA (FULL)
|
| 66 |
+
# ======================
|
| 67 |
+
def pca_full(X):
|
| 68 |
+
mean = np.mean(X, axis=0)
|
| 69 |
+
X_centered = X - mean
|
| 70 |
+
|
| 71 |
+
cov_matrix = np.cov(X_centered, rowvar=False)
|
| 72 |
+
|
| 73 |
+
eigenvalues, eigenvectors = np.linalg.eigh(cov_matrix)
|
| 74 |
+
|
| 75 |
+
idx = np.argsort(eigenvalues)[::-1]
|
| 76 |
+
eigenvectors = eigenvectors[:, idx]
|
| 77 |
+
eigenvalues = eigenvalues[idx]
|
| 78 |
+
|
| 79 |
+
return eigenvalues, eigenvectors, mean
|
| 80 |
+
|
| 81 |
+
def choose_k(eigenvalues, threshold=0.95):
|
| 82 |
+
explained_variance_ratio = eigenvalues / np.sum(eigenvalues)
|
| 83 |
+
cumulative = np.cumsum(explained_variance_ratio)
|
| 84 |
+
|
| 85 |
+
k = np.argmax(cumulative >= threshold) + 1
|
| 86 |
+
return k, cumulative
|
| 87 |
+
|
| 88 |
+
# IMPORTANT: PCA ON BALANCED TRAINING DATA
|
| 89 |
+
eigenvalues, eigenvectors, mean = pca_full(X_train_bal)
|
| 90 |
+
k, cumulative = choose_k(eigenvalues, threshold=0.95)
|
| 91 |
+
|
| 92 |
+
print(f"\nOptimal number of components: {k}")
|
| 93 |
+
|
| 94 |
+
# ======================
|
| 95 |
+
# 6. PROJECT DATA
|
| 96 |
+
# ======================
|
| 97 |
+
components = eigenvectors[:, :k]
|
| 98 |
+
|
| 99 |
+
X_train_pca = (X_train_bal - mean) @ components
|
| 100 |
+
X_test_pca = (X_test_clean - mean) @ components
|
| 101 |
+
|
| 102 |
+
print("Shape after PCA (train):", X_train_pca.shape)
|
| 103 |
+
print("Shape after PCA (test):", X_test_pca.shape)
|
| 104 |
+
|
| 105 |
+
# ======================
|
| 106 |
+
# 7. DECISION TREE
|
| 107 |
+
# ======================
|
| 108 |
+
dt = DecisionTree(maxDepth=8, minSamplesSplit=10)
|
| 109 |
+
X_train_small = X_train_bal[:5000]
|
| 110 |
+
y_train_small = y_train_bal[:5000]
|
| 111 |
+
dt.fit(X_train_small, y_train_small)
|
| 112 |
+
|
| 113 |
+
# Predict
|
| 114 |
+
predictions = dt.predict(X_test_pca)
|
| 115 |
+
|
| 116 |
+
# ======================
|
| 117 |
+
# 8. EVALUATION
|
| 118 |
+
# ======================
|
| 119 |
+
accuracy = accuracy_score(y_test_bin, predictions)
|
| 120 |
+
print("\nAccuracy:", accuracy)
|
| 121 |
+
|
| 122 |
+
cm = confusion_matrix(y_test_bin, predictions)
|
| 123 |
+
print("\nConfusion Matrix:\n", cm)
|
| 124 |
+
|
| 125 |
+
plt.figure(figsize=(6, 5))
|
| 126 |
+
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
|
| 127 |
+
plt.xlabel("Predicted")
|
| 128 |
+
plt.ylabel("Actual")
|
| 129 |
+
plt.title("Confusion Matrix (1 vs Not 1)")
|
| 130 |
+
plt.show()
|
| 131 |
+
|
| 132 |
+
print("\nClassification Report:\n")
|
| 133 |
+
print(classification_report(
|
| 134 |
+
y_test_bin, predictions,
|
| 135 |
+
target_names=["Not 1", "Is 1"]
|
| 136 |
+
))
|
| 137 |
+
|
| 138 |
+
# ======================
|
| 139 |
+
# 9. PCA SPACE VISUALIZATION
|
| 140 |
+
# ======================
|
| 141 |
+
plt.figure(figsize=(8, 6))
|
| 142 |
+
plt.scatter(X_train_pca[:, 0], X_train_pca[:, 1],
|
| 143 |
+
c=y_train_bal, cmap='coolwarm', s=5)
|
| 144 |
+
plt.xlabel("PC1")
|
| 145 |
+
plt.ylabel("PC2")
|
| 146 |
+
plt.title("PCA Space (1 vs Not 1)")
|
| 147 |
+
plt.colorbar()
|
| 148 |
+
plt.show()
|
| 149 |
+
|
| 150 |
+
# ======================
|
| 151 |
+
# 10. EXPLAINED VARIANCE
|
| 152 |
+
# ======================
|
| 153 |
+
plt.plot(cumulative)
|
| 154 |
+
plt.axhline(y=0.95, color='r', linestyle='--')
|
| 155 |
+
plt.xlabel("Number of Components")
|
| 156 |
+
plt.ylabel("Cumulative Variance")
|
| 157 |
+
plt.title("Explained Variance Curve")
|
| 158 |
+
plt.show()
|
| 159 |
+
|
| 160 |
+
# Optional: train accuracy on balanced train set
|
| 161 |
+
train_preds = dt.predict(X_train_pca)
|
| 162 |
+
print("Train Accuracy:", accuracy_score(y_train_bal, train_preds))
|
| 163 |
+
|
| 164 |
+
# Count classes in test set
|
| 165 |
+
num_6 = np.sum(y_test_bin == 1)
|
| 166 |
+
num_not6 = np.sum(y_test_bin == 0)
|
| 167 |
+
|
| 168 |
+
print("\nTest set distribution:")
|
| 169 |
+
print("Is 6:", num_6)
|
| 170 |
+
print("Not 6:", num_not6)
|
| 171 |
+
|
| 172 |
+
ratio = num_not6 / num_6
|
| 173 |
+
print("\nRatio (Not 6 : 6) =", ratio)
|
| 174 |
+
print("Ratio (6 : Not 6) = 1 :", ratio)
|
GNB/pca+VT+NAIVE_MODEL_mutli.py
ADDED
|
@@ -0,0 +1,179 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
import matplotlib.pyplot as plt
|
| 3 |
+
import seaborn as sns
|
| 4 |
+
import keras
|
| 5 |
+
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
|
| 6 |
+
|
| 7 |
+
# ======================
|
| 8 |
+
# 1. LOAD DATA
|
| 9 |
+
# ======================
|
| 10 |
+
(X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data()
|
| 11 |
+
|
| 12 |
+
# Flatten
|
| 13 |
+
X_train = X_train.reshape(X_train.shape[0], -1)
|
| 14 |
+
X_test = X_test.reshape(X_test.shape[0], -1)
|
| 15 |
+
|
| 16 |
+
# Normalize
|
| 17 |
+
X_train = X_train / 255.0
|
| 18 |
+
X_test = X_test / 255.0
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
# ======================
|
| 22 |
+
# 2. VARIANCE FILTER
|
| 23 |
+
# ======================
|
| 24 |
+
def compute_pixel_variance(X):
|
| 25 |
+
mean = np.mean(X, axis=0)
|
| 26 |
+
return np.mean((X - mean) ** 2, axis=0)
|
| 27 |
+
|
| 28 |
+
def variance_threshold(X, threshold=1e-4):
|
| 29 |
+
variances = compute_pixel_variance(X)
|
| 30 |
+
mask = variances > threshold
|
| 31 |
+
return X[:, mask], mask
|
| 32 |
+
|
| 33 |
+
X_train_clean, mask = variance_threshold(X_train)
|
| 34 |
+
X_test_clean = X_test[:, mask]
|
| 35 |
+
|
| 36 |
+
print("After variance filtering:", X_train_clean.shape)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
# ======================
|
| 40 |
+
# 3. PCA (FULL)
|
| 41 |
+
# ======================
|
| 42 |
+
def pca_full(X):
|
| 43 |
+
mean = np.mean(X, axis=0)
|
| 44 |
+
X_centered = X - mean
|
| 45 |
+
|
| 46 |
+
cov_matrix = np.cov(X_centered, rowvar=False)
|
| 47 |
+
|
| 48 |
+
eigenvalues, eigenvectors = np.linalg.eigh(cov_matrix)
|
| 49 |
+
|
| 50 |
+
idx = np.argsort(eigenvalues)[::-1]
|
| 51 |
+
eigenvectors = eigenvectors[:, idx]
|
| 52 |
+
eigenvalues = eigenvalues[idx]
|
| 53 |
+
|
| 54 |
+
return eigenvalues, eigenvectors, mean
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
def choose_k(eigenvalues, threshold=0.95):
|
| 58 |
+
explained_variance_ratio = eigenvalues / np.sum(eigenvalues)
|
| 59 |
+
cumulative = np.cumsum(explained_variance_ratio)
|
| 60 |
+
|
| 61 |
+
k = np.argmax(cumulative >= threshold) + 1
|
| 62 |
+
return k, cumulative
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
# Run PCA
|
| 66 |
+
eigenvalues, eigenvectors, mean = pca_full(X_train_clean)
|
| 67 |
+
k, cumulative = choose_k(eigenvalues, threshold=0.95)
|
| 68 |
+
|
| 69 |
+
print(f"\nOptimal number of components: {k}")
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
# ======================
|
| 73 |
+
# 4. PROJECT DATA
|
| 74 |
+
# ======================
|
| 75 |
+
components = eigenvectors[:, :k]
|
| 76 |
+
|
| 77 |
+
X_train_pca = (X_train_clean - mean) @ components
|
| 78 |
+
X_test_pca = (X_test_clean - mean) @ components
|
| 79 |
+
|
| 80 |
+
print("Shape after PCA:", X_train_pca.shape)
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
# ======================
|
| 84 |
+
# 5. GAUSSIAN NAIVE BAYES
|
| 85 |
+
# ======================
|
| 86 |
+
def gaussian_naive_train(X, y):
|
| 87 |
+
classes = np.unique(y)
|
| 88 |
+
model = {}
|
| 89 |
+
priors = {}
|
| 90 |
+
|
| 91 |
+
for c in classes:
|
| 92 |
+
X_c = X[y == c]
|
| 93 |
+
|
| 94 |
+
priors[c] = len(X_c) / len(X)
|
| 95 |
+
|
| 96 |
+
mean = np.mean(X_c, axis=0)
|
| 97 |
+
var = np.var(X_c, axis=0) + 1e-9
|
| 98 |
+
|
| 99 |
+
model[c] = (mean, var)
|
| 100 |
+
|
| 101 |
+
return model, priors
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
def predict(X, model, priors):
|
| 105 |
+
predictions = []
|
| 106 |
+
|
| 107 |
+
for x in X:
|
| 108 |
+
best_class = None
|
| 109 |
+
best_score = -float("inf")
|
| 110 |
+
|
| 111 |
+
for c in model:
|
| 112 |
+
mean, var = model[c]
|
| 113 |
+
|
| 114 |
+
log_prob = -((x - mean) ** 2) / (2 * var) - 0.5 * np.log(2 * np.pi * var)
|
| 115 |
+
score = np.log(priors[c]) + np.sum(log_prob)
|
| 116 |
+
|
| 117 |
+
if score > best_score:
|
| 118 |
+
best_score = score
|
| 119 |
+
best_class = c
|
| 120 |
+
|
| 121 |
+
predictions.append(best_class)
|
| 122 |
+
|
| 123 |
+
return np.array(predictions)
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
# Train on PCA data
|
| 127 |
+
model, priors = gaussian_naive_train(X_train_pca, y_train)
|
| 128 |
+
|
| 129 |
+
# Predict
|
| 130 |
+
predictions = predict(X_test_pca, model, priors)
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
# ======================
|
| 134 |
+
# 6. EVALUATION
|
| 135 |
+
# ======================
|
| 136 |
+
accuracy = accuracy_score(y_test, predictions)
|
| 137 |
+
print("\nAccuracy:", accuracy)
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
# Confusion Matrix
|
| 141 |
+
cm = confusion_matrix(y_test, predictions)
|
| 142 |
+
print("\nConfusion Matrix:\n", cm)
|
| 143 |
+
|
| 144 |
+
plt.figure(figsize=(8,6))
|
| 145 |
+
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
|
| 146 |
+
plt.xlabel("Predicted")
|
| 147 |
+
plt.ylabel("Actual")
|
| 148 |
+
plt.title("Confusion Matrix")
|
| 149 |
+
plt.show()
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
# Classification Report
|
| 153 |
+
print("\nClassification Report:\n")
|
| 154 |
+
print(classification_report(y_test, predictions))
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
# ======================
|
| 158 |
+
# 7. VISUALIZE PCA SPACE
|
| 159 |
+
# ======================
|
| 160 |
+
plt.figure(figsize=(8,6))
|
| 161 |
+
plt.scatter(X_train_pca[:, 0], X_train_pca[:, 1],
|
| 162 |
+
c=y_train, cmap='tab10', s=5)
|
| 163 |
+
|
| 164 |
+
plt.xlabel("PC1")
|
| 165 |
+
plt.ylabel("PC2")
|
| 166 |
+
plt.title("MNIST in PCA Space")
|
| 167 |
+
plt.colorbar()
|
| 168 |
+
plt.show()
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
# ======================
|
| 172 |
+
# 8. EXPLAINED VARIANCE
|
| 173 |
+
# ======================
|
| 174 |
+
plt.plot(cumulative)
|
| 175 |
+
plt.axhline(y=0.95, color='r', linestyle='--')
|
| 176 |
+
plt.xlabel("Number of Components")
|
| 177 |
+
plt.ylabel("Cumulative Variance")
|
| 178 |
+
plt.title("Explained Variance Curve")
|
| 179 |
+
plt.show()
|
app.py
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
import numpy as np
|
| 3 |
from skimage.feature import hog
|
| 4 |
-
from gaussian_naive_bayes import GNB
|
| 5 |
|
| 6 |
|
| 7 |
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
import numpy as np
|
| 3 |
from skimage.feature import hog
|
| 4 |
+
from GNB.gaussian_naive_bayes import GNB
|
| 5 |
|
| 6 |
|
| 7 |
|