Naive Bayes play tennis

 # Import necessary libraries

# http://bit.ly/pythonprogram9hit

from sklearn.naive_bayes import GaussianNB

from sklearn.preprocessing import LabelEncoder

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score

import pandas as pd

# Read the data from the CSV file

data = pd.read_csv("tennis.csv")

# Encode categorical variables into numerical values

label_encoder = LabelEncoder()

data_encoded = data.copy()

for column in ['Outlook', 'Temperature', 'Humidity', 'Wind', 'Play Tennis']:

    data_encoded[column] = label_encoder.fit_transform(data[column])

# Split the data into features (X) and the target variable (y)

X = data_encoded.drop('Play Tennis', axis=1)

y = data_encoded['Play Tennis']

# Split the data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=1)

# Create a Gaussian Naive Bayes model

gnb = GaussianNB()

# Fit the model to the training data

gnb.fit(X_train, y_train)

# Make predictions on the testing data

y_pred = gnb.predict(X_test)

# Calculate and print the accuracy of the model on the testing data

accuracy = accuracy_score(y_test, y_pred)

print("Accuracy on the testing data:",accuracy*100)

# #Import all necessary libraries

# import pandas as pd

# from sklearn import preprocessing

# from sklearn.naive_bayes import GaussianNB

# from sklearn import metrics

#

# #Read all data from both training and testing dataset

#

# data_train = pd.read_csv('playTennis.csv')

# data_test = pd.read_csv('playTennis.csv')

#

# #Encoding data from text into number

#

# le = preprocessing.LabelEncoder()

# data_train_df = pd.DataFrame(data_train)

# data_train_df_encoded = data_train_df.apply(le.fit_transform)

#

# data_test_df = pd.DataFrame(data_test)

# data_test_df_encoded = data_test_df.apply(le.fit_transform)

#

# #Splitting dataset into test and train variables

# x_train = data_train_df_encoded.drop(['play'],axis=1)

# y_train = data_train_df_encoded['play']

#

# x_test = data_test_df_encoded.drop(['play'],axis=1)

# y_test = data_test_df_encoded['play']

#

# #In this classification, we use GaussianNB model for prediction

# model = GaussianNB()

# nbtrain = model.fit(x_train, y_train)

#

# y_pred = nbtrain.predict(x_test)

# print("Accuracy:",metrics.accuracy_score(y_test, y_pred)*100)