Untitled

import pandas as pd

import matplotlib.pyplot as plt
startup=pd.read_csv("Data sets/Fish.csv")
print(startup)
print(startup.shape)
print(startup.columns)
print(startup['Species'].unique())
startup.isnull().sum()

print(startup.head())

startup['Species'].replace(['Bream','Roach','Whitefish','Parkki','Perch','Pike','Smelt'],[0,1,2,3,4,5,6],inplace=True)
print(startup.head())


x=startup.iloc[:,[0,2,3,4,5,6]].values
y=startup.iloc[:,1].values
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=4)

from sklearn.preprocessing import StandardScaler
sc=StandardScaler()
x_train=sc.fit_transform(x_train)
x_test=sc.fit_transform(x_test)

from sklearn.linear_model import LinearRegression
clf=LinearRegression()
clf.fit(x_train,y_train)

y_pred=clf.predict(x_test)
print("pred :",y_pred[0])
print("test :",y_test[0])

from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

r2 = r2_score(y_test, y_pred)
print("accuracy:",r2)
startup.plot.scatter(x='Species',y='Weight')