# comment: How do you compare different machine learning algorithm for accuracy in making prediction?
# comment: When Comparing, validating and choosing parameters and models use GridSearchCV (CV means Cross Validation)

# Author: Raghav RV <rvraghav93@gmail.com>
# modified for personal use by : Sam Ortega 6/13/2020 <samxcl@yahoo.com>
# License: BSD

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt

from sklearn.datasets import make_hastie_10_2
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier

print(__doc__)
print('')

# comment : Running GridSearchCV using multiple evaluation metrics

X, y = make_hastie_10_2(n_samples=8000, random_state=42)

# The scorers can be either be one of the predefined metric strings or a scorer
# callable, like the one returned by make_scorer
scoring = {'AUC': 'roc_auc', 'Accuracy': make_scorer(accuracy_score)}

# Setting refit='AUC', refits an estimator on the whole dataset with the
# parameter setting that has the best cross-validated AUC score.
# That estimator is made available at ``gs.best_estimator_`` along with
# parameters like ``gs.best_score_``, ``gs.best_params_`` and
# ``gs.best_index_``
gs = GridSearchCV(DecisionTreeClassifier(random_state=42),
                  param_grid={'min_samples_split': range(2, 403, 10)},
                  scoring=scoring, refit='AUC', return_train_score=True)
gs.fit(X, y)
results = gs.cv_results_

# comment : Plotting the result

plt.figure(figsize=(13,13))
plt.title("GridSearchCV evaluating using multiple scorers simultaneously",
          fontsize=16)

plt.xlabel("minimum_samples_split")
plt.ylabel("Score")

ax = plt.gca()
ax.set_xlim(0, 402)
ax.set_ylim(0.73, 1)

# Get the regular numpy array from the MaskedArray
X_axis = np.array(results['param_min_samples_split'].data, dtype=float)

# comment : I remember color 'g' for green, color 'k' for black , color 'r' for red
for scorer, color in zip(sorted(scoring), ['r', 'k']):

# comment : green color style used in 'train' and the line style is '--'
# comment : black color style used in 'test' and the line style is '-'
    for sample, style in (('train', '--'), ('test', '-')):
        sample_score_mean = results['mean_%s_%s' % (sample, scorer)]
        sample_score_std = results['std_%s_%s' % (sample, scorer)]
        ax.fill_between(X_axis, sample_score_mean - sample_score_std,
                        sample_score_mean + sample_score_std,
                        alpha=0.1 if sample == 'test' else 0, color=color)
        ax.plot(X_axis, sample_score_mean, style, color=color,
                alpha=1 if sample == 'test' else 0.7,
                label="%s (%s)" % (scorer, sample))

    best_index = np.nonzero(results['rank_test_%s' % scorer] == 1)[0][0]
    best_score = results['mean_test_%s' % scorer][best_index]

    # Plot a dotted vertical line at the best score for that scorer marked by x
    ax.plot([X_axis[best_index], ] * 2, [0, best_score],
            linestyle='-.', color=color, marker='x', markeredgewidth=3, ms=8)

    # Annotate the best score for that scorer
    ax.annotate("%0.2f" % best_score,
                (X_axis[best_index], best_score + 0.005))

plt.legend(loc="best")
plt.grid(False)
plt.show()

# comment # Do shift + enter
# comment # wait for 28 seconds to see the output 
# comment AUC ? means Area Under the Curve

Automatically created module for IPython interactive environment

# comment : visualizing the probability calibration

print(__doc__)
print('')

# Author: Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
# modified for personal use by : Sam Ortega 6/13/2020 <samxcl@yahoo.com>
# License: BSD Style.


import matplotlib.pyplot as plt

import numpy as np

from sklearn.datasets import make_blobs
from sklearn.ensemble import RandomForestClassifier
from sklearn.calibration import CalibratedClassifierCV
from sklearn.metrics import log_loss

np.random.seed(0)

# Generate data
X, y = make_blobs(n_samples=1000, random_state=42, cluster_std=5.0)
X_train, y_train = X[:600], y[:600]
X_valid, y_valid = X[600:800], y[600:800]
X_train_valid, y_train_valid = X[:800], y[:800]
X_test, y_test = X[800:], y[800:]

# Train uncalibrated random forest classifier on whole train and validation
# data and evaluate on test data
clf = RandomForestClassifier(n_estimators=25)
clf.fit(X_train_valid, y_train_valid)
clf_probs = clf.predict_proba(X_test)
score = log_loss(y_test, clf_probs)

# Train random forest classifier, calibrate on validation data and evaluate
# on test data
clf = RandomForestClassifier(n_estimators=25)
clf.fit(X_train, y_train)
clf_probs = clf.predict_proba(X_test)
sig_clf = CalibratedClassifierCV(clf, method="sigmoid", cv="prefit")
sig_clf.fit(X_valid, y_valid)
sig_clf_probs = sig_clf.predict_proba(X_test)
sig_score = log_loss(y_test, sig_clf_probs)

# Plot changes in predicted probabilities via arrows
plt.figure(figsize=(12,6))
colors = ["r", "g", "b"]
for i in range(clf_probs.shape[0]):
    plt.arrow(clf_probs[i, 0], clf_probs[i, 1],
              sig_clf_probs[i, 0] - clf_probs[i, 0],
              sig_clf_probs[i, 1] - clf_probs[i, 1],
              color=colors[y_test[i]], head_width=1e-2)

# Plot perfect predictions
plt.plot([1.0], [0.0], 'ro', ms=20, label="Class 1")
plt.plot([0.0], [1.0], 'go', ms=20, label="Class 2")
plt.plot([0.0], [0.0], 'bo', ms=20, label="Class 3")

# Plot boundaries of unit simplex
plt.plot([0.0, 1.0, 0.0, 0.0], [0.0, 0.0, 1.0, 0.0], 'k', label="Simplex")

# Annotate points on the simplex
plt.annotate(r'($\frac{1}{3}$, $\frac{1}{3}$, $\frac{1}{3}$)',
             xy=(1.0/3, 1.0/3), xytext=(1.0/3, .23), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.plot([1.0/3], [1.0/3], 'ko', ms=5)
plt.annotate(r'($\frac{1}{2}$, $0$, $\frac{1}{2}$)',
             xy=(.5, .0), xytext=(.5, .1), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.annotate(r'($0$, $\frac{1}{2}$, $\frac{1}{2}$)',
             xy=(.0, .5), xytext=(.1, .5), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.annotate(r'($\frac{1}{2}$, $\frac{1}{2}$, $0$)',
             xy=(.5, .5), xytext=(.6, .6), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.annotate(r'($0$, $0$, $1$)',
             xy=(0, 0), xytext=(.1, .1), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.annotate(r'($1$, $0$, $0$)',
             xy=(1, 0), xytext=(1, .1), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
plt.annotate(r'($0$, $1$, $0$)',
             xy=(0, 1), xytext=(.1, 1), xycoords='data',
             arrowprops=dict(facecolor='black', shrink=0.05),
             horizontalalignment='center', verticalalignment='center')
# Add grid
plt.grid(False)
for x in [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]:
    plt.plot([0, x], [x, 0], 'k', alpha=0.2)
    plt.plot([0, 0 + (1-x)/2], [x, x + (1-x)/2], 'k', alpha=0.2)
    plt.plot([x, x + (1-x)/2], [0, 0 + (1-x)/2], 'k', alpha=0.2)

plt.title("Change of predicted probabilities after sigmoid calibration")
plt.xlabel("Probability class 1")
plt.ylabel("Probability class 2")
plt.xlim(-0.05, 1.05)
plt.ylim(-0.05, 1.05)
plt.legend(loc="best")

print("Log-loss of")
print(" * uncalibrated classifier trained on 800 datapoints: %.3f "
      % score)
print(" * classifier trained on 600 datapoints and calibrated on "
      "200 datapoint: %.3f" % sig_score)

# Illustrate calibrator
plt.figure(figsize=(12,6))
# generate grid over 2-simplex
p1d = np.linspace(0, 1, 20)
p0, p1 = np.meshgrid(p1d, p1d)
p2 = 1 - p0 - p1
p = np.c_[p0.ravel(), p1.ravel(), p2.ravel()]
p = p[p[:, 2] >= 0]

calibrated_classifier = sig_clf.calibrated_classifiers_[0]
prediction = np.vstack([calibrator.predict(this_p)
                        for calibrator, this_p in
                        zip(calibrated_classifier.calibrators_, p.T)]).T
prediction /= prediction.sum(axis=1)[:, None]

# Plot modifications of calibrator
for i in range(prediction.shape[0]):
    plt.arrow(p[i, 0], p[i, 1],
              prediction[i, 0] - p[i, 0], prediction[i, 1] - p[i, 1],
              head_width=1e-2, color=colors[np.argmax(p[i])])
# Plot boundaries of unit simplex
plt.plot([0.0, 1.0, 0.0, 0.0], [0.0, 0.0, 1.0, 0.0], 'k', label="Simplex")

plt.grid(False)
for x in [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]:
    plt.plot([0, x], [x, 0], 'k', alpha=0.2)
    plt.plot([0, 0 + (1-x)/2], [x, x + (1-x)/2], 'k', alpha=0.2)
    plt.plot([x, x + (1-x)/2], [0, 0 + (1-x)/2], 'k', alpha=0.2)

plt.title("Illustration of sigmoid calibrator")
plt.xlabel("Probability class 1")
plt.ylabel("Probability class 2")
plt.xlim(-0.05, 1.05)
plt.ylim(-0.05, 1.05)

plt.show()

# comment # Do shift + enter
# comment: wait to see the output

Automatically created module for IPython interactive environment

Log-loss of
 * uncalibrated classifier trained on 800 datapoints: 1.280 
 * classifier trained on 600 datapoints and calibrated on 200 datapoint: 0.534

# comment :

# Author :        source: Sample from scikit-learn.org

# modified for personal use by : Sam Ortega 6/13/2020 <samxcl@yahoo.com>
# License: BSD Style.

print(__doc__)
print('')

import numpy as np
import matplotlib.pyplot as plt

from sklearn.covariance import EmpiricalCovariance, MinCovDet

n_samples = 125
n_outliers = 25
n_features = 2

# generate data
gen_cov = np.eye(n_features)
gen_cov[0, 0] = 2.
X = np.dot(np.random.randn(n_samples, n_features), gen_cov)
# add some outliers
outliers_cov = np.eye(n_features)
outliers_cov[np.arange(1, n_features), np.arange(1, n_features)] = 7.
X[-n_outliers:] = np.dot(np.random.randn(n_outliers, n_features), outliers_cov)

# fit a Minimum Covariance Determinant (MCD) robust estimator to data
robust_cov = MinCovDet().fit(X)

# compare estimators learnt from the full data set with true parameters
emp_cov = EmpiricalCovariance().fit(X)

# #############################################################################
# Display results
fig = plt.figure(figsize=(12,8))
plt.subplots_adjust(hspace=-.1, wspace=.4, top=.95, bottom=.05)

# Show data set
subfig1 = plt.subplot(3, 1, 1)
inlier_plot = subfig1.scatter(X[:, 0], X[:, 1],
                              color='black', label='inliers')
outlier_plot = subfig1.scatter(X[:, 0][-n_outliers:], X[:, 1][-n_outliers:],
                               color='red', label='outliers')
subfig1.set_xlim(subfig1.get_xlim()[0], 11.)
subfig1.set_title("Mahalanobis distances of a contaminated data set:")

# Show contours of the distance functions
xx, yy = np.meshgrid(np.linspace(plt.xlim()[0], plt.xlim()[1], 100),
                     np.linspace(plt.ylim()[0], plt.ylim()[1], 100))
zz = np.c_[xx.ravel(), yy.ravel()]

mahal_emp_cov = emp_cov.mahalanobis(zz)
mahal_emp_cov = mahal_emp_cov.reshape(xx.shape)
emp_cov_contour = subfig1.contour(xx, yy, np.sqrt(mahal_emp_cov),
                                  cmap=plt.cm.PuBu_r,
                                  linestyles='dashed')

mahal_robust_cov = robust_cov.mahalanobis(zz)
mahal_robust_cov = mahal_robust_cov.reshape(xx.shape)
robust_contour = subfig1.contour(xx, yy, np.sqrt(mahal_robust_cov),
                                 cmap=plt.cm.YlOrBr_r, linestyles='dotted')

subfig1.legend([emp_cov_contour.collections[1], robust_contour.collections[1],
                inlier_plot, outlier_plot],
               ['MLE dist', 'robust dist', 'inliers', 'outliers'],
               loc="upper right", borderaxespad=0)
plt.xticks(())
plt.yticks(())

# Plot the scores for each point
emp_mahal = emp_cov.mahalanobis(X - np.mean(X, 0)) ** (0.33)
subfig2 = plt.subplot(2, 2, 3)
subfig2.boxplot([emp_mahal[:-n_outliers], emp_mahal[-n_outliers:]], widths=.25)
subfig2.plot(np.full(n_samples - n_outliers, 1.26),
             emp_mahal[:-n_outliers], '+k', markeredgewidth=1)
subfig2.plot(np.full(n_outliers, 2.26),
             emp_mahal[-n_outliers:], '+k', markeredgewidth=1)
subfig2.axes.set_xticklabels(('inliers', 'outliers'), size=15)
subfig2.set_ylabel(r"$\sqrt[3]{\rm{(Mahal. dist.)}}$", size=16)
subfig2.set_title("1. from non-robust estimates\n(Maximum Likelihood)")
plt.yticks(())

robust_mahal = robust_cov.mahalanobis(X - robust_cov.location_) ** (0.33)
subfig3 = plt.subplot(2, 2, 4)
subfig3.boxplot([robust_mahal[:-n_outliers], robust_mahal[-n_outliers:]],
                widths=.25)
subfig3.plot(np.full(n_samples - n_outliers, 1.26),
             robust_mahal[:-n_outliers], '+k', markeredgewidth=1)
subfig3.plot(np.full(n_outliers, 2.26),
             robust_mahal[-n_outliers:], '+k', markeredgewidth=1)
subfig3.axes.set_xticklabels(('inliers', 'outliers'), size=15)
subfig3.set_ylabel(r"$\sqrt[3]{\rm{(Mahal. dist.)}}$", size=16)
subfig3.set_title("2. from robust estimates\n(Minimum Covariance Determinant)")
plt.yticks(())

plt.show()

# comment # Do shift + enter
# comment :

Automatically created module for IPython interactive environment

# comment : Using a robust estimator of covariance to guarantee that the estimation is resistant 
# to “erroneous” observations in the data set.

# Author :        source: Sample from scikit-learn.org

# modified for personal use by : Sam Ortega 6/13/2020 <samxcl@yahoo.com>
# License: BSD Style.

print(__doc__)
print('')

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.font_manager

from sklearn.covariance import EmpiricalCovariance, MinCovDet

# example settings
n_samples = 80
n_features = 5
repeat = 10

range_n_outliers = np.concatenate(
    (np.linspace(0, n_samples / 8, 5),
     np.linspace(n_samples / 8, n_samples / 2, 5)[1:-1])).astype(np.int)

# definition of arrays to store results
err_loc_mcd = np.zeros((range_n_outliers.size, repeat))
err_cov_mcd = np.zeros((range_n_outliers.size, repeat))
err_loc_emp_full = np.zeros((range_n_outliers.size, repeat))
err_cov_emp_full = np.zeros((range_n_outliers.size, repeat))
err_loc_emp_pure = np.zeros((range_n_outliers.size, repeat))
err_cov_emp_pure = np.zeros((range_n_outliers.size, repeat))

# computation
for i, n_outliers in enumerate(range_n_outliers):
    for j in range(repeat):

        rng = np.random.RandomState(i * j)

        # generate data
        X = rng.randn(n_samples, n_features)
        # add some outliers
        outliers_index = rng.permutation(n_samples)[:n_outliers]
        outliers_offset = 10. * \
            (np.random.randint(2, size=(n_outliers, n_features)) - 0.5)
        X[outliers_index] += outliers_offset
        inliers_mask = np.ones(n_samples).astype(bool)
        inliers_mask[outliers_index] = False

        # fit a Minimum Covariance Determinant (MCD) robust estimator to data
        mcd = MinCovDet().fit(X)
        # compare raw robust estimates with the true location and covariance
        err_loc_mcd[i, j] = np.sum(mcd.location_ ** 2)
        err_cov_mcd[i, j] = mcd.error_norm(np.eye(n_features))

        # compare estimators learned from the full data set with true
        # parameters
        err_loc_emp_full[i, j] = np.sum(X.mean(0) ** 2)
        err_cov_emp_full[i, j] = EmpiricalCovariance().fit(X).error_norm(
            np.eye(n_features))

        # compare with an empirical covariance learned from a pure data set
        # (i.e. "perfect" mcd)
        pure_X = X[inliers_mask]
        pure_location = pure_X.mean(0)
        pure_emp_cov = EmpiricalCovariance().fit(pure_X)
        err_loc_emp_pure[i, j] = np.sum(pure_location ** 2)
        err_cov_emp_pure[i, j] = pure_emp_cov.error_norm(np.eye(n_features))

# Display results
font_prop = matplotlib.font_manager.FontProperties(size=11)
plt.figure(figsize=(12,10))
plt.subplot(2, 1, 1)
lw = 2
plt.errorbar(range_n_outliers, err_loc_mcd.mean(1),
             yerr=err_loc_mcd.std(1) / np.sqrt(repeat),
             label="Robust location", lw=lw, color='m')
plt.errorbar(range_n_outliers, err_loc_emp_full.mean(1),
             yerr=err_loc_emp_full.std(1) / np.sqrt(repeat),
             label="Full data set mean", lw=lw, color='green')
plt.errorbar(range_n_outliers, err_loc_emp_pure.mean(1),
             yerr=err_loc_emp_pure.std(1) / np.sqrt(repeat),
             label="Pure data set mean", lw=lw, color='black')
plt.title("Influence of outliers on the location estimation", size=14)
plt.ylabel(r"Error ($||\mu - \hat{\mu}||_2^2$)", size=12)
plt.legend(loc="upper left", prop=font_prop)

plt.subplot(2, 1, 2)
x_size = range_n_outliers.size
plt.errorbar(range_n_outliers, err_cov_mcd.mean(1),
             yerr=err_cov_mcd.std(1),
             label="Robust covariance (mcd)", color='m')
plt.errorbar(range_n_outliers[:(x_size // 5 + 1)],
             err_cov_emp_full.mean(1)[:(x_size // 5 + 1)],
             yerr=err_cov_emp_full.std(1)[:(x_size // 5 + 1)],
             label="Full data set empirical covariance", color='green')
plt.plot(range_n_outliers[(x_size // 5):(x_size // 2 - 1)],
         err_cov_emp_full.mean(1)[(x_size // 5):(x_size // 2 - 1)],
         color='green', ls='--')
plt.errorbar(range_n_outliers, err_cov_emp_pure.mean(1),
             yerr=err_cov_emp_pure.std(1),
             label="Pure data set empirical covariance", color='black')
plt.title("Influence of outliers on the covariance estimation", size=14)
plt.xlabel("Amount of contamination (%)")
plt.ylabel("RMSE")
plt.legend(loc="upper center", prop=font_prop)

plt.show()

# comment # Do shift + enter
# wait to see the output
# Minimum Covariance Determinant estimator (MCD) 

Automatically created module for IPython interactive environment

# comment : How to plot in 3D the three principal component using PCA
# modified for personal use by : Sam Ortega 6/13/2020 <samxcl@yahoo.com>


# Code source: Gaël Varoquaux
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause

print(__doc__)
print('')

import seaborn as sns
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn import datasets
from sklearn.decomposition import PCA

# import some data to play with
iris = datasets.load_iris()
X = iris.data[:, :2]  # we only take the first two features or fieldname column 
y = iris.target

x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5

plt.figure(1, figsize=(8, 6))
plt.clf()

# Plot the training points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1,
            edgecolor='k')
plt.xlabel('Sepal length, x-axis', size=12)
plt.ylabel('Sepal width, y-axis', size = 12)

plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())



# To getter a better understanding of interaction of the dimensions
# plot the first three PCA dimensions
fig = plt.figure(2, figsize=(9, 7))
ax = Axes3D(fig, elev=-150, azim=110)


X_reduced = PCA(n_components=3).fit_transform(iris.data)
ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2],  c=y,
           cmap=plt.cm.Set1, edgecolor='k', s=40)
ax.set_title("First three PCA directions")
ax.set_xlabel("1st eigenvector ")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("2nd eigenvector ")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("3rd eigenvector ")
ax.w_zaxis.set_ticklabels([])

plt.show()

# comment # Do shift + enter
# comment : wait to use the output

Automatically created module for IPython interactive environment

# comment show me the first 20 records of iris data set
# iris = pd.read_excel('/Users/invbat/projects/mpg.xlsx')
iris = pd.read_excel('/Users/invbat/projects/iris.xlsx')
iris.head(20)
# comment # Do shift + enter
# comment : wait to see the output

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa
5	5.4	3.9	1.7	0.4	setosa
6	4.6	3.4	1.4	0.3	setosa
7	5.0	3.4	1.5	0.2	setosa
8	4.4	2.9	1.4	0.2	setosa
9	4.9	3.1	1.5	0.1	setosa
10	5.4	3.7	1.5	0.2	setosa
11	4.8	3.4	1.6	0.2	setosa
12	4.8	3.0	1.4	0.1	setosa
13	4.3	3.0	1.1	0.1	setosa
14	5.8	4.0	1.2	0.2	setosa
15	5.7	4.4	1.5	0.4	setosa
16	5.4	3.9	1.3	0.4	setosa
17	5.1	3.5	1.4	0.3	setosa
18	5.7	3.8	1.7	0.3	setosa
19	5.1	3.8	1.5	0.3	setosa

# comment : Get me the answer, how many total rows of record used in iris table? using .info() function
# the answer is 150 records or observation.
iris.info()
# comment # Do shift + enter

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   sepal_length  150 non-null    float64
 1   sepal_width   150 non-null    float64
 2   petal_length  150 non-null    float64
 3   petal_width   150 non-null    float64
 4   species       150 non-null    object 
dtypes: float64(4), object(1)
memory usage: 6.0+ KB

# comment : I want to see the pairwise analysis for PCA

sns.pairplot(iris);

# comment # Do shift + enter
# comment: wait to see the ouput