import lazypredict

from lazypredict.Supervised import LazyClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

data = load_breast_cancer()
X = data.data
y = data.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=123)

clf = LazyClassifier(verbose=0, ignore_warnings=True, custom_metric=None)
models, predictions = clf.fit(X_train, X_test, y_train, y_test)

print(models)

# With categorical encoding, timeout, and cross-validation
clf = LazyClassifier(
    verbose=1,                          # Show progress
    ignore_warnings=True,               # Suppress warnings
    custom_metric=None,                 # Use default metrics
    predictions=True,                   # Return predictions
    classifiers='all',                  # Use all available classifiers
    categorical_encoder='onehot',       # Encoding: 'onehot', 'ordinal', 'target', 'binary'
    timeout=60,                         # Max time per model in seconds
    cv=5                                # Cross-validation folds (optional)
)
models, predictions = clf.fit(X_train, X_test, y_train, y_test)

from lazypredict.Supervised import LazyRegressor
from sklearn import datasets
from sklearn.utils import shuffle
import numpy as np

diabetes  = datasets.load_diabetes()
X, y = shuffle(diabetes.data, diabetes.target, random_state=13)
X = X.astype(np.float32)

offset = int(X.shape[0] * 0.9)

X_train, y_train = X[:offset], y[:offset]
X_test, y_test = X[offset:], y[offset:]

reg = LazyRegressor(verbose=0, ignore_warnings=False, custom_metric=None)
models, predictions = reg.fit(X_train, X_test, y_train, y_test)

print(models)

# With categorical encoding and timeout
reg = LazyRegressor(
    verbose=1,                          # Show progress
    ignore_warnings=True,               # Suppress warnings
    custom_metric=None,                 # Use default metrics
    predictions=True,                   # Return predictions
    regressors='all',                   # Use all available regressors
    categorical_encoder='ordinal',      # Encoding: 'onehot', 'ordinal', 'target', 'binary'
    timeout=120                         # Max time per model in seconds
)
models, predictions = reg.fit(X_train, X_test, y_train, y_test)

import numpy as np
from lazypredict.TimeSeriesForecasting import LazyForecaster

# Generate sample data (or use your own)
np.random.seed(42)
t = np.arange(200)
y = 10 + 0.05 * t + 3 * np.sin(2 * np.pi * t / 12) + np.random.normal(0, 1, 200)

y_train, y_test = y[:180], y[180:]

fcst = LazyForecaster(verbose=0, ignore_warnings=True)
scores, predictions = fcst.fit(y_train, y_test)
print(scores)

# Optional exogenous features
X_train = np.column_stack([np.sin(t[:180]), np.cos(t[:180])])
X_test = np.column_stack([np.sin(t[180:]), np.cos(t[180:])])

scores, predictions = fcst.fit(y_train, y_test, X_train, X_test)

fcst = LazyForecaster(
    verbose=1,                          # Show progress
    ignore_warnings=True,               # Suppress model errors
    predictions=True,                   # Return forecast values
    seasonal_period=12,                 # Override auto-detection
    cv=3,                               # Time series cross-validation
    timeout=30,                         # Max seconds per model
    sort_by="RMSE",                     # Sort metric (MAE, MAPE, SMAPE, MASE, R-Squared)
    forecasters="all",                  # Or list: ["Holt", "AutoARIMA", "LSTM_TS"]
    max_models=10,                      # Limit number of models
)
scores, predictions = fcst.fit(y_train, y_test)

from lazypredict.Supervised import LazyClassifier
import pandas as pd
from sklearn.model_selection import train_test_split

# Example with categorical features
df = pd.read_csv('data_with_categories.csv')
X = df.drop('target', axis=1)
y = df['target']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

# Try different encoders
for encoder in ['onehot', 'ordinal', 'target', 'binary']:
    clf = LazyClassifier(
        categorical_encoder=encoder,
        verbose=0,
        ignore_warnings=True
    )
    models, predictions = clf.fit(X_train, X_test, y_train, y_test)
    print(f"\n{encoder.upper()} Encoding Results:")
    print(models.head())

import os
os.environ['MLFLOW_TRACKING_URI'] = 'sqlite:///mlflow.db'

# MLflow tracking will be automatically enabled
reg = LazyRegressor(verbose=0, ignore_warnings=True)
models, predictions = reg.fit(X_train, X_test, y_train, y_test)