classifier_random forrest_important features

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 

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

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# Any results you write to the current directory are saved as output


#---------import dataset 
data = '/kaggle/input/car-evaluation-data-set/car_evaluation.csv'

df = pd.read_csv(data, header=None)

#Rename column names
#We can see that the dataset does not have proper column names. The columns are merely labelled as 0,1,2.... and so on. We should give proper names to the columns. I will do it as follows:-

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


df.columns = col_names

col_names




X = df.drop(['class'], axis=1)

y = df['class']

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 = 42)


#Encode cateogorical variables
X_train.dtypes

import category_encoders as ce
encoder = ce.OrdinalEncoder(cols=['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety'])


X_train = encoder.fit_transform(X_train)

X_test = encoder.transform(X_test)



#------------------------Train Basic---------------------
rfc_100 = RandomForestClassifier(n_estimators=100, random_state=0)
rfc_100.fit(X_train, y_train)
# 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_test, y_pred_100))

#--------------Random forrest feature importance
clf = RandomForestClassifier(n_estimators=100, random_state=0)

# fit the model to the training set

clf.fit(X_train, y_train
feature_scores = pd.Series(clf.feature_importances_, index=X_train.columns).sort_values(ascending=False)

repeat the process
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
print('Confusion matrix\n\n', cm)
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))