Data Science Project at Beginner Level Using Python. Prediction using Supervised ML смотреть онлайн

Prediction using Supervised ML
Prediction of the percentage of a student based on the no. of study hours.
Using Python

GitHub: https://bit.ly/3i0IpGa
Source:
Data File http://bit.ly/w-data
Code :

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import metrics

# Data Importing & Reading
url = "http://bit.ly/w-data"
data = pd.read_csv(url)
print("Data Imported")
print(data.head(20)

data.info()
data.describe()
# Plotting to check correlation
data.plot(x ='Hours', y ='Scores', style='o')
plt.title("Hrs Vs Score", fontsize = 18 ,fontweight = "bold" )
plt.xlabel("Hrs")
plt.ylabel("Score")
plt.show()

# Regression Graph
sns.regplot(x=data["Hours"],y=data["Scores"], data=data, scatter_kws={'color': "c"}, line_kws={'color': "b"})
plt.title("Hrs Vs Score", fontsize = 18 ,fontweight = "bold" )
plt.xlabel("Hrs")
plt.ylabel("Score")
plt.show()

# Model Training
x = data.iloc[:, :-1].values
y = data.iloc[:, 1].values
x_train,x_test,y_train,y_test = train_test_split(x,y, random_state=0)
regression = LinearRegression()
regression.fit(x_train, y_train)
print('Trained')


# Actual Vs Predict
y_pred = regression.predict(x_test)
df = pd.DataFrame({'Acutal': y_test, 'Predicted': y_pred})

# Mean Absolute Error
print(" mean absolute error:", metrics.mean_absolute_error(y_test, y_pred))

Hours = [9.25]
own_pred = regression.predict([Hours])
print("Numbrer of Hours = {}".format([Hours]))
print("Predicted Score = {}".format(own_pred[0]))

print(df)
line = regression.coef_* x + regression.intercept_