# Suppress warnings for a clean notebook
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Load the digits dataset from sklearn
from sklearn.datasets import load_digits
digits = load_digits()
X, y = digits.data, digits.target
print(X.shape)
print(y.shape)

# Display the first 5 rows of data
import pandas as pd
df = pd.DataFrame(X)
print(df.head())

# Visualize some sample digit images
import matplotlib.pyplot as plt
fig, axes = plt.subplots(1, 5, figsize=(10, 3))
for i, ax in enumerate(axes):
    ax.imshow(digits.images[i], cmap="gray_r")
    ax.set_title(f"Label: {digits.target[i]}")
    ax.axis("off")
plt.show()

# Check for missing data
import numpy as np
missing = np.isnan(X).sum()
print(f"Total missing values: {missing}")

# Split the data into train and test sets
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print(X_train.shape, X_test.shape)

# Look at the label distribution in the training set
unique, counts = np.unique(y_train, return_counts=True)
for value, count in zip(unique, counts):
    print(f"Digit {value}: {count} samples")

# Scale the features for better model performance
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Train a logistic regression model
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(max_iter=1000, solver="lbfgs", multi_class="auto", random_state=42)
clf.fit(X_train_scaled, y_train)

# Predict on the test set
y_pred = clf.predict(X_test_scaled)
print(y_pred[:10])

# Measure model accuracy
from sklearn.metrics import accuracy_score
acc = accuracy_score(y_test, y_pred)
print(f"Accuracy: {acc:.2f}")

# Show model performance for each digit
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))

# Visualize results: show predictions vs actuals
fig, axes = plt.subplots(2, 5, figsize=(12, 5))
for i, ax in enumerate(axes.flat):
    idx = i
    ax.imshow(X_test[idx].reshape(8,8), cmap="gray_r")
    ax.set_title(f"Pred:{y_pred[idx]}, True:{y_test[idx]}")
    ax.axis("off")
plt.tight_layout()
plt.show()

# Confusion matrix: where does the model get confused?
import seaborn as sns
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8,6))
sns.heatmap(cm, annot=True, fmt="d", cmap="YlGnBu")
plt.xlabel("Predicted")
plt.ylabel("True")
plt.title("Confusion Matrix")
plt.show()

# Try a different model: K Nearest Neighbors
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_scaled, y_train)
knn_pred = knn.predict(X_test_scaled)
knn_acc = accuracy_score(y_test, knn_pred)
print(f"KNN Accuracy: {knn_acc:.2f}")

# Time series: visualize digit counts over index
import matplotlib.pyplot as plt
digits_per_index = pd.Series(y).value_counts().sort_index()
plt.figure(figsize=(8,4))
plt.plot(digits_per_index.index, digits_per_index.values, marker="o")
plt.title("Sample Count By Digit Value")
plt.xlabel("Digit")
plt.ylabel("Count")
plt.show()