first commit

app.py

@@ -0,0 +1,87 @@
+import streamlit as st
+import tensorflow as tf
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+import numpy as np
+import matplotlib.pyplot as plt
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.models import Sequential
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.metrics import mean_squared_error
+
+# Define the custom loss function
+def soft_quantized_influence_measure(y_true, y_pred, threshold=0.1):
+    y_global_mean = tf.reduce_mean(y_true)
+    y_std = tf.math.reduce_std(y_true)
+    error = y_true - y_pred
+    abs_error = tf.abs(error)
+    is_small_error = abs_error <= threshold
+    n1 = tf.reduce_sum(tf.cast(is_small_error, tf.float32))
+    n2 = tf.reduce_sum(tf.cast(~is_small_error, tf.float32))
+    true_error_loss = tf.square(error) * n1 ** 2
+    false_error_loss = tf.square(error) * n2 ** 2
+    final = tf.where(is_small_error, true_error_loss, false_error_loss)
+    final = tf.reduce_mean(final) / (tf.square(y_std) ** 2)
+    return final
+
+# Function to create datasets
+def create_datasets(n_samples=1500):
+    noisy_circles = datasets.make_circles(n_samples=n_samples, factor=0.5, noise=0.05, random_state=170)
+    noisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05, random_state=170)
+    blobs = datasets.make_blobs(n_samples=n_samples, random_state=170)
+    rng = np.random.RandomState(170)
+    no_structure = rng.rand(n_samples, 2), None
+    X, y = datasets.make_blobs(n_samples=n_samples, random_state=170)
+    transformation = [[0.6, -0.6], [-0.4, 0.8]]
+    X_aniso = np.dot(X, transformation)
+    aniso = (X_aniso, y)
+    return [noisy_circles, noisy_moons, blobs, no_structure, aniso]
+
+# Function to create a simple one-layer neural network
+def create_model(input_shape):
+    model = Sequential([Dense(1, input_shape=input_shape, activation='sigmoid')])
+    return model
+
+# Main app
+def main():
+    st.title("Classification Data and Model Training Visualization")
+
+    # Data generation
+    datasets = create_datasets()
+    dataset_names = ["Noisy Circles", "Noisy Moons", "Blobs", "No Structure", "Anisotropic"]
+
+    # Streamlit selections for visualization
+    selected_dataset = st.selectbox("Select a Dataset", options=dataset_names)
+
+    # Placeholder for plots
+    fig, axs = plt.subplots(3, len(datasets), figsize=(15, 9))
+
+    # Encoder for labels
+    encoder = OneHotEncoder(sparse=False)
+
+    for i, dataset in enumerate(datasets):
+        X, y = dataset
+        if y is not None:
+            y = encoder.fit_transform(y.reshape(-1, 1))
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+        # First row - Original datasets
+        if y is not None:
+            axs[0, i].scatter(X[:, 0], X[:, 1], c=np.argmax(y, axis=1))
+        else:
+            axs[0, i].scatter(X[:, 0], X[:, 1])
+        axs[0, i].set_title(dataset_names[i])
+
+        # Create model
+        model = create_model((2,))
+
+        # MSE Loss
+        model.compile(optimizer='sgd', loss='mean_squared_error')
+        history_mse = model.fit(X_train, y_train, validation_split=0.2, epochs=20, verbose=0)
+
+        # Soft Quantized Influence Measure Loss
+        model.compile(optimizer='sgd', loss=lambda y_true, y_pred: soft_quantized_influence_measure(y_true, y_pred, 0.1))
+        history_sqim = model.fit(X_train, y_train, validation_split=0.2, epochs=20, verbose=0)
+
+        # Second row - MSE Loss
+        axs[1, i].plot

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+tensorflow
+scikit-learn
+matplotlib
+numpy