58 lines
2.1 KiB
Python
58 lines
2.1 KiB
Python
|
import numpy as np
|
||
|
|
import pandas as pb
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
from sklearn.linear_model import LinearRegression, Perceptron, LogisticRegression, Lasso, Ridge
|
||
|
|
from sklearn.neural_network import MLPClassifier, MLPRegressor
|
||
|
|
from sklearn.pipeline import make_pipeline
|
||
|
|
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, MinMaxScaler
|
||
|
|
from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier
|
||
|
|
from sklearn.preprocessing import PolynomialFeatures
|
||
|
|
|
||
|
|
df = pb.read_csv("StudentsPerformance.csv", sep=",", encoding="windows-1251")
|
||
|
|
df1 = df
|
||
|
|
print("Данные без подготовки:")
|
||
|
|
with pb.option_context('display.max_rows', None, 'display.max_columns', None, 'display.width', 1000):
|
||
|
|
print(df[:5])
|
||
|
|
|
||
|
|
def prepareStringData(columnName):
|
||
|
|
uniq = df[columnName].unique()
|
||
|
|
mp = {}
|
||
|
|
for i in uniq:
|
||
|
|
mp[i] = len(mp)
|
||
|
|
df[columnName] = df[columnName].map(mp)
|
||
|
|
|
||
|
|
|
||
|
|
print()
|
||
|
|
print("Данные после подготовки:")
|
||
|
|
prepareStringData("gender")
|
||
|
|
prepareStringData("race/ethnicity")
|
||
|
|
prepareStringData("parental level of education")
|
||
|
|
prepareStringData("lunch")
|
||
|
|
prepareStringData("test preparation course")
|
||
|
|
with pb.option_context('display.max_rows', None, 'display.max_columns', None, 'display.width', 1000):
|
||
|
|
print(df[:5])
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
X = df[["gender", "race/ethnicity", "lunch", "test preparation course", "parental level of education", "reading score", "writing score"]]
|
||
|
|
y = df["math score"]
|
||
|
|
X_train, X_Test, y_train, y_test = train_test_split(X, y, test_size=0.26, random_state=42)
|
||
|
|
lnr = LinearRegression()
|
||
|
|
lnr = lnr.fit(X_train,y_train)
|
||
|
|
|
||
|
|
poly_regression = make_pipeline(PolynomialFeatures(degree=4), LinearRegression())
|
||
|
|
poly_regression.fit(X_train, y_train)
|
||
|
|
|
||
|
|
lasso = Lasso()
|
||
|
|
lasso.fit(X_train, y_train)
|
||
|
|
|
||
|
|
ridge = Ridge()
|
||
|
|
ridge.fit(X_train, y_train)
|
||
|
|
|
||
|
|
|
||
|
|
print("Линейная регрессия: ", lnr.score(X_Test,y_test))
|
||
|
|
print("Полиномиальная регрессия: ", poly_regression.score(X_Test,y_test))
|
||
|
|
print("Лассо-регрессия: ", lasso.score(X_Test,y_test))
|
||
|
|
print("Гребневая регрессия: ", ridge.score(X_Test,y_test))
|