import 

numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt # data visualization
import seaborn as sns # statistical data visualization
%matplotlib inline
 

from google.colab import files
uploaded = files.upload()

Choose Files No file chosen

Upload widget is only available when the cell has been
executed in the
current browser session. Please rerun this cell to enable.
Saving car evaluation(1).csv to car evaluation(1) (2).csv

import io
df = pd.read_csv(io.BytesIO(uploaded['car_evaluation(1).csv']))
df

vhigh vhigh.1 2 2.1 small low unacc

0 vhigh vhigh 2 2 small med unacc

1 vhigh vhigh 2 2 small high unacc

2 vhigh vhigh 2 2 med low unacc

3 vhigh vhigh 2 2 med med unacc

4 vhigh vhigh 2 2 med high unacc

... ... ... ... ... ... ... ...

1722 low low 5more more med med good

1723 low low 5more more med high vgood

1724 low low 5more more big low unacc

1725 low low 5more more big med good

1726 low low 5more more big high vgood

1727 rows × 7 columns

df.shape

(1727, 7)

df.head()
 vhigh vhigh.1 2 2.1 small low unacc

0 vhigh vhigh 2 2 small med unacc

1 vhigh vhigh 2 2 small high unacc

2 vhigh vhigh 2 2 med low unacc

3 vhigh vhigh 2 2 med med unacc

df 4 vhigh vhigh 2 2 med high unacc

vhigh vhigh.1 2 2.1 small low unacc

0 vhigh vhigh 2 2 small med unacc

1 vhigh vhigh 2 2 small high unacc

2 vhigh vhigh 2 2 med low unacc

3 vhigh vhigh 2 2 med med unacc

4 vhigh vhigh 2 2 med high unacc

... ... ... ... ... ... ... ...

1722 low low 5more more med med good

1723 low low 5more more med high vgood

1724 low low 5more more big low unacc

1725 low low 5more more big med good

1726 low low 5more more big high vgood

1727 rows × 7 columns

col_names = ['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety', 'class']

df.columns = col_names

col_names

['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety', 'class']

df.head()
 buying maint doors persons lug_boot safety class
#summary of data set
0 vhigh vhigh 2 2 small med unacc
 
  1 vhigh vhigh 2 2 small high unacc
df.info()
  2 vhigh vhigh 2 2 med low unacc
  3 vhigh vhigh 2 2 med med unacc

<class
4 'pandas.core.frame.DataFrame'>

vhigh vhigh 2 2 med high unacc

RangeIndex: 1727 entries, 0 to 1726

Data columns (total 7 columns):

# Column Non-Null Count Dtype

--- ------ -------------- -----

0 buying 1727 non-null object

1 maint 1727 non-null object

2 doors 1727 non-null object

3 persons 1727 non-null object

4 lug_boot 1727 non-null object

5 safety 1727 non-null object

6 class 1727 non-null object

dtypes: object(7)

memory usage: 94.6+ KB

#
#Frequency distribution of values in variables
 
#Now, check the frequency counts of categorical variables.
col_names = ['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety', 'class']
 
 
for col in col_names:
    
    print(df[col].value_counts())  
 

high 432

med 432

low 432

vhigh 431

Name: buying, dtype: int64

high 432

med 432

low 432

vhigh 431

Name: maint, dtype: int64

3 432

4 432

5more 432

2 431

Name: doors, dtype: int64

4 576

more 576

2 575

Name: persons, dtype: int64

big 576

med 576

small 575

 Name: lug_boot, dtype: int64

high 576

med 576

low 575

Name: safety, dtype: int64

unacc 1209

acc 384

good 69

vgood 65

Name: class, dtype: int64

 
 
df['class'].value_counts()
 
 

unacc 1209

acc 384

good 69

vgood 65

Name: class, dtype: int64

# check missing values in variables
df.isnull().sum()

buying 0

maint 0

doors 0

persons 0

lug_boot 0

safety 0

class 0

dtype: int64

#Declare feature vector and target variable 
X = df.drop(['class'], axis=1)
 
y = df['class']

X
 buying maint doors persons lug_boot safety

0 vhigh vhigh 2 2 small med

1 vhigh vhigh 2 2 small high

2 vhigh vhigh 2 2 med low

3 vhigh vhigh 2 2 med med

4 vhigh vhigh 2 2 med high

y ... ... ... ... ... ... ...

01722 unacc

low low 5more more med med

1 unacc

21723 low
unacc
low 5more more med high
3 unacc

41724 low
unacc
low 5more more big low
...

1725 low low 5more more big med

1722 good

1723
1726 vgood

low low 5more more big high

1724 unacc

1725 good

1727 rows × 6 columns

1726 vgood

Name: class, Length: 1727, dtype: object

#Split data into separate training and test set 
from sklearn.model_selection import train_test_split
 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33, random_state = 
 

# check the shape of X_train and X_test
 
X_train.shape, X_test.shape

((1157, 6), (570, 6))

#Feature Engineering 
# check data types in X_train
 
X_train.dtypes

buying object

maint object

doors object

persons object

lug_boot object

safety object

dtype: object

#Encode categorical variables
X_train.head()
 buying maint doors persons lug_boot safety

83 vhigh vhigh 5more 2 med low

48 vhigh vhigh 3 more med med

468 high vhigh 3 4 small med

155 vhigh high 3 more med low

1043 med high 4 more small low

pip install category_encoders

Requirement already satisfied: category_encoders in /usr/local/lib/python3.7/dist-pac

Requirement already satisfied: numpy>=1.14.0 in /usr/local/lib/python3.7/dist-package
Requirement already satisfied: patsy>=0.5.1 in /usr/local/lib/python3.7/dist-packages
Requirement already satisfied: statsmodels>=0.9.0 in /usr/local/lib/python3.7/dist-pa
Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.7/dist-
Requirement already satisfied: scipy>=1.0.0 in /usr/local/lib/python3.7/dist-packages
Requirement already satisfied: pandas>=0.21.1 in /usr/local/lib/python3.7/dist-packag
Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dis
Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages
Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from pa
Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages

# import category encoders
 
import category_encoders as ce

# encode categorical variables with ordinal encoding
 
encoder = ce.OrdinalEncoder(cols=['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safe

 
X_train = encoder.fit_transform(X_train)
 
X_test = encoder.transform(X_test)

/usr/local/lib/python3.7/dist-packages/category_encoders/utils.py:21: FutureWarning:
elif pd.api.types.is_categorical(cols):

X_train.head()
 buying maint doors persons lug_boot safety

83
X_test.head() 1 1 1 1 1 1

48 1 1 2 2 1 2
buying maint doors persons lug_boot safety
468 2 1 2 3 2 2
599 2 2 3 1 3 1
155 1 2 2 2 1 1
932 3 1 3 3 3 1
1043 3 2 3 2 2 1
628 2 2 1 1 3 3

1497 4 2 1 3 1 2

1262 3 4 3 2 1 1

 
 
# import Random Forest classifier
 
from sklearn.ensemble import RandomForestClassifier

# instantiate the classifier 
 
rfc = RandomForestClassifier(random_state=0)
 

# fit the model
 
rfc.fit(X_train, y_train)
 

RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,

criterion='gini', max_depth=None, max_features='auto',

max_leaf_nodes=None, max_samples=None,

min_impurity_decrease=0.0, min_impurity_split=None,

min_samples_leaf=1, min_samples_split=2,

min_weight_fraction_leaf=0.0, n_estimators=100,

n_jobs=None, oob_score=False, random_state=0, verbose=0,

warm_start=False)

# Predict the Test set results
 
y_pred = rfc.predict(X_test)
 

# Check accuracy score 
 
from sklearn.metrics import accuracy_score
 
#print('Model accuracy score with 10 decision-trees : {0:0.4f}'. format(accuracy_score(y_t

#H b ild th R d F t Cl ifi d l ith d f lt t f ti t

#Here, we build the Random Forest Classifier model with default parameter of n_estimators 

# instantiate the classifier with n_estimators = 100
 
rfc_100 = RandomForestClassifier(n_estimators=100, random_state=0)

# fit the model to the training set
 
rfc_100.fit(X_train, y_train)
 

RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,

criterion='gini', max_depth=None, max_features='auto',

max_leaf_nodes=None, max_samples=None,

min_impurity_decrease=0.0, min_impurity_split=None,

min_samples_leaf=1, min_samples_split=2,

min_weight_fraction_leaf=0.0, n_estimators=100,

n_jobs=None, oob_score=False, random_state=0, verbose=0,

warm_start=False)

# Predict on the test set results
 
y_pred_100 = rfc_100.predict(X_test)
 

 
# Check accuracy score 
 
print('Model accuracy score with 100 decision-trees : {0:0.4f}'. format(accuracy_score(y_t

Model accuracy score with 100 decision-trees : 0.9649

#Find important features with Random Forest model 
# create the classifier with n_estimators = 100
 
clf = RandomForestClassifier(n_estimators=100, random_state=0)

# fit the model to the training set
 
clf.fit(X_train, y_train)

RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,

criterion='gini', max_depth=None, max_features='auto',

max_leaf_nodes=None, max_samples=None,

min_impurity_decrease=0.0, min_impurity_split=None,

min_samples_leaf=1, min_samples_split=2,

min_weight_fraction_leaf=0.0, n_estimators=100,

n_jobs=None, oob_score=False, random_state=0, verbose=0,

warm_start=False)

# view the feature scores
 
feature scores = pd Series(clf feature importances index=X train columns) sort values(as
feature_scores = pd.Series(clf.feature_importances_, index=X_train.columns).sort_values(as
 
feature_scores

safety 0.291657

persons 0.235380

buying 0.160692

maint 0.134143

lug_boot 0.111595

doors 0.066533

dtype: float64

# Creating a seaborn bar plot
 
sns.barplot(x=feature_scores, y=feature_scores.index)
# Add title to the graph
 
plt.title("Visualizing Important Features")
 
 
 
# Visualize the graph
 
plt.show()
 

#Build Random Forest model on selected features
# declare feature vector and target variable
 
X = df.drop(['class', 'doors'], axis=1)
 
y = df['class']

# split data into training and testing sets
 
from sklearn.model_selection import train_test_split
 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33, random_state = 
X

buying maint persons lug_boot safety

0 vhigh vhigh 2 small med

1 vhigh vhigh 2 small high

2 vhigh vhigh 2 med low

3 vhigh vhigh 2 med med

4 vhigh vhigh 2 med high

... ... ... ... ... ...

1722 low low more med med

1723 low low more med high

1724 low low more big low

1725 low low more big med

1726 low low more big high

1727 rows × 5 columns

 #encode categorical variables with ordinal encoding
 
encoder = ce.OrdinalEncoder(cols=['buying', 'maint', 'persons', 'lug_boot', 'safety'])
 
 
X_train = encoder.fit_transform(X_train)
 
X_test = encoder.transform(X_test)

/usr/local/lib/python3.7/dist-packages/category_encoders/utils.py:21: FutureWarning:
elif pd.api.types.is_categorical(cols):

# instantiate the classifier with n_estimators = 100
 
clf = RandomForestClassifier(random_state=0)

# fit the model to the training set
 
clf.fit(X_train, y_train)

RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,

criterion='gini', max_depth=None, max_features='auto',

max_leaf_nodes=None, max_samples=None,

min_impurity_decrease=0.0, min_impurity_split=None,

min_samples_leaf=1, min_samples_split=2,

min_weight_fraction_leaf=0.0, n_estimators=100,

n_jobs=None, oob_score=False, random_state=0, verbose=0,

warm_start=False)
# Predict on the test set results
 
y_pred = clf.predict(X_test)
 

# Check accuracy score 
 
print('Model accuracy score with doors variable removed : {0:0.4f}'. format(accuracy_score

Model accuracy score with doors variable removed : 0.9263

 
# Classification Report
 
 
 
#Classification report is another way to evaluate the classification model performance. It 
 
#We can print a classification report as follows:-
 
from sklearn.metrics import classification_report
 
print(classification_report(y_test, y_pred))
 
 

precision recall f1-score support

acc 0.88 0.85 0.86 127

good 0.62 0.56 0.59 18

unacc 0.97 0.97 0.97 399

vgood 0.75 0.81 0.78 26

accuracy 0.93 570

macro avg 0.80 0.80 0.80 570

weighted avg 0.93 0.93 0.93 570