import pandas as pd

from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing(return_X_y=False)

df = pd.DataFrame(housing.data, columns=housing.feature_names)
df['target'] = housing.target
target='target'
df

import sys
import warnings
warnings.simplefilter(action='ignore')

import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(df[df.columns[:-1]], df[target], test_size=0.25)

!pip install sweetviz

import sweetviz as sv

my_report = sv.analyze(df)

# we generate html report
# Default arguments will generate to "SWEETVIZ_REPORT.html"
my_report.show_html() 

# we generate inline report
my_report.show_notebook()

!pip install ydata_profiling
#!pip install matplotlib==3.1.3

from ydata_profiling import ProfileReport

profile = ProfileReport(df, title="Profiling Report")

#To generate a HTML report file, save the ProfileReport to an object and use the to_file() function:
profile.to_file("ydata_profiling.html")

#The HTML report can be directly embedded in a cell in a similar fashion:
profile.to_notebook_iframe()

!pip install mljar-supervised[full]

from supervised.automl import AutoML
#automl = AutoML(mode="Perform",results_path="AutoML_regression")
#automl = AutoML(mode="Explain"results_path="AutoML_regression")
automl = AutoML(results_path="AutoML_regression")
automl.fit(X_train, y_train)

y_predicted = automl.predict(X_test)
y_predicted

pd.read_csv('/content/AutoML_regression/leaderboard.csv')

import imageio

def show_image(file):
  im=imageio.imread(file)
  plt.figure(figsize=(8,8))
  plt.imshow(im)
  plt.show()

show_image('/content/AutoML_regression/features_heatmap.png')
show_image('/content/AutoML_regression/ldb_performance_boxplot.png')
show_image('/content/AutoML_regression/correlation_heatmap.png')
show_image('/content/AutoML_regression/Ensemble/true_vs_predicted.png')
show_image('/content/AutoML_regression/30_LightGBM/permutation_importance.png')


!pip install tpot

from tpot import TPOTRegressor

tpot = TPOTRegressor(generations=2, population_size=50, verbosity=2, random_state=42)
tpot.fit(X_train, y_train)

print(tpot.score(X_test, y_test))
tpot.export('TPOTRegressor_pipeline.py')