Hướng dẫn Scikit-Learn: Cách cài đặt và ví dụ về Scikit-Learn

import sys
!{sys.executable} -m pip install git+git://github.com/scikit-learn/scikit-learn.git

source activate hello-tf

conda remove scikit-learn

conda install -c anaconda git
pip install Cython
pip install h5py
pip install git+git://github.com/scikit-learn/scikit-learn.git

## List Categorical
CATE_FEATURES = df_train.iloc[:,:-1].select_dtypes('object').columns
print(CATE_FEATURES)

## List continuous
CONTI_FEATURES =  df_train._get_numeric_data()
print(CONTI_FEATURES)

# Import dataset
import pandas as pd

## Define path data
COLUMNS = ['age','workclass', 'fnlwgt', 'education', 'education_num', 'marital',
           'occupation', 'relationship', 'race', 'sex', 'capital_gain', 'capital_loss',
           'hours_week', 'native_country', 'label']
### Define continuous list
CONTI_FEATURES  = ['age', 'fnlwgt','capital_gain', 'education_num', 'capital_loss', 'hours_week']
### Define categorical list
CATE_FEATURES = ['workclass', 'education', 'marital', 'occupation', 'relationship', 'race', 'sex', 'native_country']

## Prepare the data
features = ['age','workclass', 'fnlwgt', 'education', 'education_num', 'marital',
           'occupation', 'relationship', 'race', 'sex', 'capital_gain', 'capital_loss',
           'hours_week', 'native_country']

PATH = "https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data"

df_train = pd.read_csv(PATH, skipinitialspace=True, names = COLUMNS, index_col=False)
df_train[CONTI_FEATURES] =df_train[CONTI_FEATURES].astype('float64')
df_train.describe()

df_train.native_country.value_counts()

United-States                 29170
Mexico                          643
?                               583
Philippines                     198
Germany                         137
Canada                          121
Puerto-Rico                     114
El-Salvador                     106
India                           100
Cuba                             95
England                          90
Jamaica                          81
South                            80
China                            75
Italy                            73
Dominican-Republic               70
Vietnam                          67
Guatemala                        64
Japan                            62
Poland                           60
Columbia                         59
Taiwan                           51
Haiti                            44
Iran                             43
Portugal                         37
Nicaragua                        34
Peru                             31
France                           29
Greece                           29
Ecuador                          28
Ireland                          24
Hong                             20
Cambodia                         19
Trinadad&Tobago                  19
Thailand                         18
Laos                             18
Yugoslavia                       16
Outlying-US(Guam-USVI-etc)       14
Honduras                         13
Hungary                          13
Scotland                         12
Holand-Netherlands                1
Name: native_country, dtype: int64

## Drop Netherland, because only one row
df_train = df_train[df_train.native_country != "Holand-Netherlands"]

## Get the column index of the categorical features
conti_features = []
for i in CONTI_FEATURES:
    position = df_train.columns.get_loc(i)
    conti_features.append(position)
print(conti_features)  

[0, 2, 10, 4, 11, 12]

## Get the column index of the categorical features
categorical_features = []
for i in CATE_FEATURES:
    position = df_train.columns.get_loc(i)
    categorical_features.append(position)
print(categorical_features)  

[1, 3, 5, 6, 7, 8, 9, 13]

df_train.head(5)

print(df_train[CATE_FEATURES].nunique(),
      'There are',sum(df_train[CATE_FEATURES].nunique()), 'groups in the whole dataset')

workclass          9
education         16
marital            7
occupation        15
relationship       6
race               5
sex                2
native_country    41
dtype: int64 There are 101 groups in the whole dataset

for i in CATE_FEATURES:
    print(df_train[i].unique())

['State-gov' 'Self-emp-not-inc' 'Private' 'Federal-gov' 'Local-gov' '?'
 'Self-emp-inc' 'Without-pay' 'Never-worked']
['Bachelors' 'HS-grad' '11th' 'Masters' '9th' 'Some-college' 'Assoc-acdm'
 'Assoc-voc' '7th-8th' 'Doctorate' 'Prof-school' '5th-6th' '10th'
 '1st-4th' 'Preschool' '12th']
['Never-married' 'Married-civ-spouse' 'Divorced' 'Married-spouse-absent'
 'Separated' 'Married-AF-spouse' 'Widowed']
['Adm-clerical' 'Exec-managerial' 'Handlers-cleaners' 'Prof-specialty'
 'Other-service' 'Sales' 'Craft-repair' 'Transport-moving'
 'Farming-fishing' 'Machine-op-inspct' 'Tech-support' '?'
 'Protective-serv' 'Armed-Forces' 'Priv-house-serv']
['Not-in-family' 'Husband' 'Wife' 'Own-child' 'Unmarried' 'Other-relative']
['White' 'Black' 'Asian-Pac-Islander' 'Amer-Indian-Eskimo' 'Other']
['Male' 'Female']
['United-States' 'Cuba' 'Jamaica' 'India' '?' 'Mexico' 'South'
 'Puerto-Rico' 'Honduras' 'England' 'Canada' 'Germany' 'Iran'
 'Philippines' 'Italy' 'Poland' 'Columbia' 'Cambodia' 'Thailand' 'Ecuador'
 'Laos' 'Taiwan' 'Haiti' 'Portugal' 'Dominican-Republic' 'El-Salvador'
 'France' 'Guatemala' 'China' 'Japan' 'Yugoslavia' 'Peru'
 'Outlying-US(Guam-USVI-etc)' 'Scotland' 'Trinadad&Tobago' 'Greece'
 'Nicaragua' 'Vietnam' 'Hong' 'Ireland' 'Hungary']

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(df_train[features],
                                                    df_train.label,
                                                    test_size = 0.2,
                                                    random_state=0)
X_train.head(5)
print(X_train.shape, X_test.shape)

(26048, 14) (6512, 14)

from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
from sklearn.compose import ColumnTransformer, make_column_transformer
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression

preprocess = make_column_transformer(
    (conti_features, StandardScaler()),
    ### Need to be numeric not string to specify columns name 
    (categorical_features, OneHotEncoder(sparse=False))
)

preprocess.fit_transform(X_train).shape

(26048, 107)

model = make_pipeline(
    preprocess,
    LogisticRegression())

model.fit(X_train, y_train)
print("logistic regression score: %f" % model.score(X_test, y_test))

logistic regression score: 0.850891

model.predict_proba(X_test)

array([[0.83576663, 0.16423337],
       [0.94582765, 0.05417235],
       [0.64760587, 0.35239413],
       ...,
       [0.99639252, 0.00360748],
       [0.02072181, 0.97927819],
       [0.56781353, 0.43218647]])

from sklearn.model_selection import GridSearchCV
# Construct the parameter grid
param_grid = {
    'logisticregression__C': [0.001, 0.01,0.1, 1.0],
    }

# Train the model
grid_clf = GridSearchCV(model,
                        param_grid,
                        cv=10,
                        iid=False)
grid_clf.fit(X_train, y_train)

GridSearchCV(cv=10, error_score='raise-deprecating',
       estimator=Pipeline(memory=None,
     steps=[('columntransformer', ColumnTransformer(n_jobs=1, remainder='drop', transformer_weights=None,
         transformers=[('standardscaler', StandardScaler(copy=True, with_mean=True, with_std=True), [0, 2, 10, 4, 11, 12]), ('onehotencoder', OneHotEncoder(categorical_features=None, categories=None,...ty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False))]),
       fit_params=None, iid=False, n_jobs=1,
       param_grid={'logisticregression__C': [0.001, 0.01, 0.1, 1.0]},
       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',
       scoring=None, verbose=0)

grid_clf.best_params_

{'logisticregression__C': 1.0}

print("best logistic regression from grid search: %f" % grid_clf.best_estimator_.score(X_test, y_test))

grid_clf.best_estimator_.predict_proba(X_test)

array([[0.83576677, 0.16423323],
       [0.9458291 , 0.0541709 ],
       [0.64760416, 0.35239584],
       ...,
       [0.99639224, 0.00360776],
       [0.02072033, 0.97927967],
       [0.56782222, 0.43217778]])

use import sys
!{sys.executable} -m pip install xgboost

import xgboost
from sklearn.model_selection import RandomizedSearchCV
from sklearn.model_selection import StratifiedKFold

params = {
        'xgbclassifier__gamma': [0.5, 1],
        'xgbclassifier__max_depth': [3, 4]
        }

model_xgb = make_pipeline(
    preprocess,
    xgboost.XGBClassifier(
                          n_estimators=600,
                          objective='binary:logistic',
                          silent=True,
                          nthread=1)
)

skf = StratifiedKFold(n_splits=3,
                      shuffle = True,
                      random_state = 1001)

random_search = RandomizedSearchCV(model_xgb,
                                   param_distributions=params,
                                   n_iter=4,
                                   scoring='accuracy',
                                   n_jobs=4,
                                   cv=skf.split(X_train, y_train),
                                   verbose=3,
                                   random_state=1001)

#grid_xgb = GridSearchCV(model_xgb, params, cv=10, iid=False)
random_search.fit(X_train, y_train)

Fitting 3 folds for each of 4 candidates, totalling 12 fits
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5 ............
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5 ............
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5 ............
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5 ............
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5, score=0.8759645283888057, total= 1.0min
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5 ............
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5, score=0.8729701715996775, total= 1.0min
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=0.5, score=0.8706519235199263, total= 1.0min
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5 ............
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5, score=0.8735460094437406, total= 1.3min
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=1, score=0.8722791661868018, total=  57.7s
[CV] xgbclassifier__max_depth=3, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=1, score=0.8753886905447426, total= 1.0min
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5, score=0.8697304768486523, total= 1.3min
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=0.5, score=0.8740066797189912, total= 1.4min
[CV] xgbclassifier__max_depth=4, xgbclassifier__gamma=1 ..............
[CV]  xgbclassifier__max_depth=3, xgbclassifier__gamma=1, score=0.8707671043538355, total= 1.0min
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=1, score=0.8729701715996775, total= 1.2min
[Parallel(n_jobs=4)]: Done  10 out of  12 | elapsed:  3.6min remaining:   43.5s
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=1, score=0.8736611770125533, total= 1.2min
[CV]  xgbclassifier__max_depth=4, xgbclassifier__gamma=1, score=0.8692697535130154, total= 1.2min

[Parallel(n_jobs=4)]: Done  12 out of  12 | elapsed:  3.6min finished
/Users/Thomas/anaconda3/envs/hello-tf/lib/python3.6/site-packages/sklearn/model_selection/_search.py:737: DeprecationWarning: The default of the `iid` parameter will change from True to False in version 0.22 and will be removed in 0.24. This will change numeric results when test-set sizes are unequal. DeprecationWarning)

RandomizedSearchCV(cv=<generator object _BaseKFold.split at 0x1101eb830>,
          error_score='raise-deprecating',
          estimator=Pipeline(memory=None,
     steps=[('columntransformer', ColumnTransformer(n_jobs=1, remainder='drop', transformer_weights=None,
         transformers=[('standardscaler', StandardScaler(copy=True, with_mean=True, with_std=True), [0, 2, 10, 4, 11, 12]), ('onehotencoder', OneHotEncoder(categorical_features=None, categories=None,...
       reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,
       silent=True, subsample=1))]),
          fit_params=None, iid='warn', n_iter=4, n_jobs=4,
          param_distributions={'xgbclassifier__gamma': [0.5, 1], 'xgbclassifier__max_depth': [3, 4]},
          pre_dispatch='2*n_jobs', random_state=1001, refit=True,
          return_train_score='warn', scoring='accuracy', verbose=3)

print("Best parameter", random_search.best_params_)
print("best logistic regression from grid search: %f" % random_search.best_estimator_.score(X_test, y_test))

Best parameter {'xgbclassifier__max_depth': 3, 'xgbclassifier__gamma': 0.5}
best logistic regression from grid search: 0.873157

random_search.best_estimator_.predict(X_test)

array(['<=50K', '<=50K', '<=50K', ..., '<=50K', '>50K', '<=50K'],      dtype=object)

from sklearn.neural_network import MLPClassifier

model_dnn = make_pipeline(
    preprocess,
    MLPClassifier(solver='adam',
                  alpha=0.0001,
                  activation='relu',
                    batch_size=150,
                    hidden_layer_sizes=(200, 100),
                    random_state=1))

model_dnn.fit(X_train, y_train)
  print("DNN regression score: %f" % model_dnn.score(X_test, y_test))

df_train.head(5)
# Create numpy data
df_lime = df_train
df_lime.head(3)

# Get the class name
class_names = df_lime.label.unique()
class_names

array(['<=50K', '>50K'], dtype=object)

## 
import sklearn.preprocessing as preprocessing
categorical_names = {}
for feature in CATE_FEATURES:
    le = preprocessing.LabelEncoder()
    le.fit(df_lime[feature])
    df_lime[feature] = le.transform(df_lime[feature])
    categorical_names[feature] = le.classes_
print(categorical_names)    

{'workclass': array(['?', 'Federal-gov', 'Local-gov', 'Never-worked', 'Private',
       'Self-emp-inc', 'Self-emp-not-inc', 'State-gov', 'Without-pay'],
      dtype=object), 'education': array(['10th', '11th', '12th', '1st-4th', '5th-6th', '7th-8th', '9th',
       'Assoc-acdm', 'Assoc-voc', 'Bachelors', 'Doctorate', 'HS-grad',
       'Masters', 'Preschool', 'Prof-school', 'Some-college'],
      dtype=object), 'marital': array(['Divorced', 'Married-AF-spouse', 'Married-civ-spouse',
       'Married-spouse-absent', 'Never-married', 'Separated', 'Widowed'],
      dtype=object), 'occupation': array(['?', 'Adm-clerical', 'Armed-Forces', 'Craft-repair',
       'Exec-managerial', 'Farming-fishing', 'Handlers-cleaners',
       'Machine-op-inspct', 'Other-service', 'Priv-house-serv',
       'Prof-specialty', 'Protective-serv', 'Sales', 'Tech-support',
       'Transport-moving'], dtype=object), 'relationship': array(['Husband', 'Not-in-family', 'Other-relative', 'Own-child',
       'Unmarried', 'Wife'], dtype=object), 'race': array(['Amer-Indian-Eskimo', 'Asian-Pac-Islander', 'Black', 'Other',
       'White'], dtype=object), 'sex': array(['Female', 'Male'], dtype=object), 'native_country': array(['?', 'Cambodia', 'Canada', 'China', 'Columbia', 'Cuba',
       'Dominican-Republic', 'Ecuador', 'El-Salvador', 'England',
       'France', 'Germany', 'Greece', 'Guatemala', 'Haiti', 'Honduras',
       'Hong', 'Hungary', 'India', 'Iran', 'Ireland', 'Italy', 'Jamaica',
       'Japan', 'Laos', 'Mexico', 'Nicaragua',
       'Outlying-US(Guam-USVI-etc)', 'Peru', 'Philippines', 'Poland',
       'Portugal', 'Puerto-Rico', 'Scotland', 'South', 'Taiwan',
       'Thailand', 'Trinadad&Tobago', 'United-States', 'Vietnam',
       'Yugoslavia'], dtype=object)}

df_lime.dtypes

age               float64
workclass           int64
fnlwgt            float64
education           int64
education_num     float64
marital             int64
occupation          int64
relationship        int64
race                int64
sex                 int64
capital_gain      float64
capital_loss      float64
hours_week        float64
native_country      int64
label              object
dtype: object

from sklearn.model_selection import train_test_split
X_train_lime, X_test_lime, y_train_lime, y_test_lime = train_test_split(df_lime[features],
                                                    df_lime.label,
                                                    test_size = 0.2,
                                                    random_state=0)
X_train_lime.head(5)

model_xgb = make_pipeline(
    preprocess,
    xgboost.XGBClassifier(max_depth = 3,
                          gamma = 0.5,
                          n_estimators=600,
                          objective='binary:logistic',
                          silent=True,
                          nthread=1))

model_xgb.fit(X_train_lime, y_train_lime)

/Users/Thomas/anaconda3/envs/hello-tf/lib/python3.6/site-packages/sklearn/preprocessing/_encoders.py:351: FutureWarning: The handling of integer data will change in version 0.22. Currently, the categories are determined based on the range [0, max(values)], while in the future they will be determined based on the unique values.
If you want the future behavior and silence this warning, you can specify "categories='auto'."In case you used a LabelEncoder before this OneHotEncoder to convert the categories to integers, then you can now use the OneHotEncoder directly.
  warnings.warn(msg, FutureWarning)

Pipeline(memory=None,
     steps=[('columntransformer', ColumnTransformer(n_jobs=1, remainder='drop', transformer_weights=None,
         transformers=[('standardscaler', StandardScaler(copy=True, with_mean=True, with_std=True), [0, 2, 10, 4, 11, 12]), ('onehotencoder', OneHotEncoder(categorical_features=None, categories=None,...
       reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,
       silent=True, subsample=1))])

print("best logistic regression from grid search: %f" % model_xgb.score(X_test_lime, y_test_lime))

best logistic regression from grid search: 0.873157

model_xgb.predict_proba(X_test_lime)

array([[7.9646105e-01, 2.0353897e-01],
       [9.5173013e-01, 4.8269872e-02],
       [7.9344827e-01, 2.0655173e-01],
       ...,
       [9.9031430e-01, 9.6856682e-03],
       [6.4581633e-04, 9.9935418e-01],
       [9.7104281e-01, 2.8957171e-02]], dtype=float32)

temp = pd.concat([X_test_lime, y_test_lime], axis= 1)
temp['predicted'] = model_xgb.predict(X_test_lime)
temp['wrong']=  temp['label'] != temp['predicted']
temp = temp.query('wrong==True').drop('wrong', axis=1)
temp= temp.sort_values(by=['label'])
temp.shape

predict_fn = lambda x: model_xgb.predict_proba(x).astype(float)
X_test_lime.dtypes

age               float64
workclass           int64
fnlwgt            float64
education           int64
education_num     float64
marital             int64
occupation          int64
relationship        int64
race                int64
sex                 int64
capital_gain      float64
capital_loss      float64
hours_week        float64
native_country      int64
dtype: object

predict_fn(X_test_lime)

array([[7.96461046e-01, 2.03538969e-01],
       [9.51730132e-01, 4.82698716e-02],
       [7.93448269e-01, 2.06551731e-01],
       ...,
       [9.90314305e-01, 9.68566816e-03],
       [6.45816326e-04, 9.99354184e-01],
       [9.71042812e-01, 2.89571714e-02]])

X_train_lime = X_train_lime.values
X_test_lime = X_test_lime.values
X_test_lime

array([[4.00000e+01, 5.00000e+00, 1.93524e+05, ..., 0.00000e+00,
        4.00000e+01, 3.80000e+01],
       [2.70000e+01, 4.00000e+00, 2.16481e+05, ..., 0.00000e+00,
        4.00000e+01, 3.80000e+01],
       [2.50000e+01, 4.00000e+00, 2.56263e+05, ..., 0.00000e+00,
        4.00000e+01, 3.80000e+01],
       ...,
       [2.80000e+01, 6.00000e+00, 2.11032e+05, ..., 0.00000e+00,
        4.00000e+01, 2.50000e+01],
       [4.40000e+01, 4.00000e+00, 1.67005e+05, ..., 0.00000e+00,
        6.00000e+01, 3.80000e+01],
       [5.30000e+01, 4.00000e+00, 2.57940e+05, ..., 0.00000e+00,
        4.00000e+01, 3.80000e+01]])

model_xgb.predict_proba(X_test_lime)

array([[7.9646105e-01, 2.0353897e-01],
       [9.5173013e-01, 4.8269872e-02],
       [7.9344827e-01, 2.0655173e-01],
       ...,
       [9.9031430e-01, 9.6856682e-03],
       [6.4581633e-04, 9.9935418e-01],
       [9.7104281e-01, 2.8957171e-02]], dtype=float32)

print(features,
      class_names,
      categorical_features,
      categorical_names)

['age', 'workclass', 'fnlwgt', 'education', 'education_num', 'marital', 'occupation', 'relationship', 'race', 'sex', 'capital_gain', 'capital_loss', 'hours_week', 'native_country'] ['<=50K' '>50K'] [1, 3, 5, 6, 7, 8, 9, 13] {'workclass': array(['?', 'Federal-gov', 'Local-gov', 'Never-worked', 'Private',
       'Self-emp-inc', 'Self-emp-not-inc', 'State-gov', 'Without-pay'],
      dtype=object), 'education': array(['10th', '11th', '12th', '1st-4th', '5th-6th', '7th-8th', '9th',
       'Assoc-acdm', 'Assoc-voc', 'Bachelors', 'Doctorate', 'HS-grad',
       'Masters', 'Preschool', 'Prof-school', 'Some-college'],
      dtype=object), 'marital': array(['Divorced', 'Married-AF-spouse', 'Married-civ-spouse',
       'Married-spouse-absent', 'Never-married', 'Separated', 'Widowed'],
      dtype=object), 'occupation': array(['?', 'Adm-clerical', 'Armed-Forces', 'Craft-repair',
       'Exec-managerial', 'Farming-fishing', 'Handlers-cleaners',
       'Machine-op-inspct', 'Other-service', 'Priv-house-serv',
       'Prof-specialty', 'Protective-serv', 'Sales', 'Tech-support',
       'Transport-moving'], dtype=object), 'relationship': array(['Husband', 'Not-in-family', 'Other-relative', 'Own-child',
       'Unmarried', 'Wife'], dtype=object), 'race': array(['Amer-Indian-Eskimo', 'Asian-Pac-Islander', 'Black', 'Other',
       'White'], dtype=object), 'sex': array(['Female', 'Male'], dtype=object), 'native_country': array(['?', 'Cambodia', 'Canada', 'China', 'Columbia', 'Cuba',
       'Dominican-Republic', 'Ecuador', 'El-Salvador', 'England',
       'France', 'Germany', 'Greece', 'Guatemala', 'Haiti', 'Honduras',
       'Hong', 'Hungary', 'India', 'Iran', 'Ireland', 'Italy', 'Jamaica',
       'Japan', 'Laos', 'Mexico', 'Nicaragua',
       'Outlying-US(Guam-USVI-etc)', 'Peru', 'Philippines', 'Poland',
       'Portugal', 'Puerto-Rico', 'Scotland', 'South', 'Taiwan',
       'Thailand', 'Trinadad&Tobago', 'United-States', 'Vietnam',
       'Yugoslavia'], dtype=object)}

import lime
import lime.lime_tabular
### Train should be label encoded not one hot encoded
explainer = lime.lime_tabular.LimeTabularExplainer(X_train_lime ,
                                                   feature_names = features,
                                                   class_names=class_names,
                                                   categorical_features=categorical_features, 
                                                   categorical_names=categorical_names,
                                                   kernel_width=3)

import numpy as np
np.random.seed(1)
i = 100
print(y_test_lime.iloc[i])
>50K

X_test_lime[i]

array([4.20000e+01, 4.00000e+00, 1.76286e+05, 7.00000e+00, 1.20000e+01,
       2.00000e+00, 4.00000e+00, 0.00000e+00, 4.00000e+00, 1.00000e+00,
       0.00000e+00, 0.00000e+00, 4.00000e+01, 3.80000e+01])

exp = explainer.explain_instance(X_test_lime[i], predict_fn, num_features=6)
exp.show_in_notebook(show_all=False)

temp.head(3)
temp.iloc[1,:-2]

age                  58
workclass             4
fnlwgt            68624
education            11
education_num         9
marital               2
occupation            4
relationship          0
race                  4
sex                   1
capital_gain          0
capital_loss          0
hours_week           45
native_country       38
Name: 20931, dtype: object

i = 1
print('This observation is', temp.iloc[i,-2:])

This observation is label        <=50K
predicted     >50K
Name: 20931, dtype: object

exp = explainer.explain_instance(temp.iloc[1,:-2], predict_fn, num_features=6)
exp.show_in_notebook(show_all=False)