We have seen the introduction of Lazypredict and Regression models to make our life easy to check which models better for our data.

In this blog, we will go through a code of the Lazypredict Classifier problem. I have prepared my own data and posted it onto the GitHub repository to download this data.

In this example, I am going to use Jupyter Notebook. I have prepared my own data and posted it onto the GitHub repository to download this data.

Copy to Clipboard

#Install lazypredict
pip install lazypredict

 
#Install lazypredict
pip install lazypredict

Copy to Clipboard

#Import Lazypredict and all libraries
import lazypredict
from lazypredict.Supervised import LazyClassifier
from sklearn.model_selection import train_test_split
import os
import pandas as pd
pd.set_option('float_format', '{:f}'.format)
import numpy as np

 
#Import Lazypredict and all libraries
import lazypredict
from lazypredict.Supervised import LazyClassifier
from sklearn.model_selection import train_test_split
import os
import pandas as pd
pd.set_option('float_format', '{:f}'.format)
import numpy as np

Copy to Clipboard

#Function to download and read delivery data CSV file
DATA_FILES_PATH = r"C:\\Users\\gchandr4\\Documents\\Blogs\\LazyPredict Classifier"
def load_customer_data(data_path=DATA_FILES_PATH):
    csv_path = os.path.join(data_path, "delivery_days_classifier.csv")
    return pd.read_csv(csv_path)

 
#Function to download and read delivery data CSV file
DATA_FILES_PATH = r"C:\\Users\\gchandr4\\Documents\\Blogs\\LazyPredict Classifier"
def load_customer_data(data_path=DATA_FILES_PATH):
    csv_path = os.path.join(data_path, "delivery_days_classifier.csv")
    return pd.read_csv(csv_path)

Copy to Clipboard

#load the data
data = load_customer_data()

 
#load the data
data = load_customer_data()

Copy to Clipboard

#Print Data
data.head()

 
#Print Data
data.head()

Copy to Clipboard

#Split data into X and y target
X = data[['Sold To', 'Ship To', 'Material', 'Price/Qty (USD)', 'Qty', 'Total Price (USD)', 'no_of_delivery_days']]
y = data[['target_ouput']]

 
#Split data into X and y target
X = data[['Sold To', 'Ship To', 'Material', 'Price/Qty (USD)', 'Qty', 'Total Price (USD)', 'no_of_delivery_days']]
y = data[['target_ouput']]

Copy to Clipboard

X

X

Copy to Clipboard

y

y

Copy to Clipboard

X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=.5,random_state =123)

 
X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=.5,random_state =123)

Copy to Clipboard

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

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

Copy to Clipboard

print(models)

 
print(models)

                               Accuracy  Balanced Accuracy  ROC AUC  F1 Score  \
Model                                                                           
AdaBoostClassifier             1.000000           1.000000 1.000000  1.000000   
LinearDiscriminantAnalysis     1.000000           1.000000 1.000000  1.000000   
XGBClassifier                  1.000000           1.000000 1.000000  1.000000   
SGDClassifier                  1.000000           1.000000 1.000000  1.000000   
RidgeClassifierCV              1.000000           1.000000 1.000000  1.000000   
RidgeClassifier                1.000000           1.000000 1.000000  1.000000   
RandomForestClassifier         1.000000           1.000000 1.000000  1.000000   
Perceptron                     1.000000           1.000000 1.000000  1.000000   
PassiveAggressiveClassifier    1.000000           1.000000 1.000000  1.000000   
NearestCentroid                1.000000           1.000000 1.000000  1.000000   
LogisticRegression             1.000000           1.000000 1.000000  1.000000   
BaggingClassifier              1.000000           1.000000 1.000000  1.000000   
LinearSVC                      1.000000           1.000000 1.000000  1.000000   
GaussianNB                     1.000000           1.000000 1.000000  1.000000   
ExtraTreesClassifier           1.000000           1.000000 1.000000  1.000000   
DecisionTreeClassifier         1.000000           1.000000 1.000000  1.000000   
CalibratedClassifierCV         1.000000           1.000000 1.000000  1.000000   
BernoulliNB                    1.000000           1.000000 1.000000  1.000000   
LGBMClassifier                 1.000000           1.000000 1.000000  1.000000   
SVC                            0.998000           0.997642 0.997642  0.997999   
QuadraticDiscriminantAnalysis  0.992000           0.990566 0.990566  0.991989   
NuSVC                          0.984000           0.981132 0.981132  0.983956   
KNeighborsClassifier           0.978000           0.974679 0.974679  0.977931   
ExtraTreeClassifier            0.960000           0.961544 0.961544  0.960089   
LabelSpreading                 0.960000           0.957187 0.957187  0.959919   
LabelPropagation               0.960000           0.957187 0.957187  0.959919   
DummyClassifier                0.508000           0.494497 0.494497  0.507005   

                               Time Taken  
Model                                      
AdaBoostClassifier               0.021941  
LinearDiscriminantAnalysis       0.000000  
XGBClassifier                    0.029637  
SGDClassifier                    0.012965  
RidgeClassifierCV                0.015958  
RidgeClassifier                  0.017968  
RandomForestClassifier           0.147104  
Perceptron                       0.000000  
PassiveAggressiveClassifier      0.015622  
NearestCentroid                  0.011968  
LogisticRegression               0.026497  
BaggingClassifier                0.039891  
LinearSVC                        0.015622  
GaussianNB                       0.015621  
ExtraTreesClassifier             0.136031  
DecisionTreeClassifier           0.017724  
CalibratedClassifierCV           0.023703  
BernoulliNB                      0.012965  
LGBMClassifier                   0.053272  
SVC                              0.008027  
QuadraticDiscriminantAnalysis    0.017415  
NuSVC                            0.014008  
KNeighborsClassifier             0.044704  
ExtraTreeClassifier              0.012965  
LabelSpreading                   0.031243  
LabelPropagation                 0.014095  
DummyClassifier                  0.011968

Many classifiers works best for this data.