import pandas as pd

df = pd.read_csv("https://raw.githubusercontent.com/pplonski/datasets-for-start/master/adult/data.csv",skipinitialspace=True,)
target = 'income'
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)

try:
    import sweetviz as sv
except:
    !pip install sweetviz --user
    print('Restart runtime to import 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()

# port_intra.show_my_report_intra = sv.compare_intra(df, df["sex"] == "Male", ["Male", "Female"])
# my_renotebook()

try:
    import ydata_profiling
except:
    !pip install ydata_profiling
    import ydata_profiling

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()

try:
  from supervised.automl import AutoML
except:
  !pip install mljar-supervised
  from supervised.automl import AutoML

automl = AutoML(mode="Perform",results_path="AutoML_classifier")
# automl = AutoML(mode="Explain",results_path="AutoML_classifier")
#automl = AutoML(results_path="AutoML_classifier")
automl.fit(X_train, y_train)

y_predicted = automl.predict(X_test)
y_predicted

from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_predicted)

#print(automl.score(X_test1, y_test))

pd.read_csv('/content/AutoML_classifier/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_classifier/features_heatmap.png')
show_image('/content/AutoML_classifier/ldb_performance_boxplot.png')
show_image('/content/AutoML_classifier/correlation_heatmap.png')
show_image('/content/AutoML_classifier/Ensemble/confusion_matrix.png')
show_image('/content/AutoML_classifier/Ensemble/precision_recall_curve.png')
show_image('/content/AutoML_classifier/Ensemble/roc_curve.png')
show_image('/content/AutoML_classifier/38_CatBoost/permutation_importance.png')

# automl1 = AutoML(algorithms=["CatBoost"],mode="Optuna", start_random_models=3)
# automl1.fit(X_train, y_train)

try:
  from lazypredict.Supervised import LazyClassifier
except:
  !pip install lazypredict
  from lazypredict.Supervised import LazyClassifier

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

#!pip install tpot

# X_train1 = pd.get_dummies(X_train).values
# X_test1 = pd.get_dummies(X_test).values
# #X_train1 = X_train
# #X_test1 = X_test

# from tpot import TPOTClassifier
# tpot = TPOTClassifier(generations=2, population_size=50, verbosity=2, random_state=42)
# tpot.fit(X_train1, y_train)

# tpot.export('TPOTClassifier_pipeline.py')

#!pip install -U scikit-learn==0.23.2
#!pip install --use-deprecated=legacy-resolver pycaret[full]

#from pycaret.classification import *
#s = setup(df, target = target)

#best = compare_models()

#print(best)
#plot_model(best)

#evaluate_model(best)