通过多项式回归解锁准确的预测

date = [ { "study_time": 1, "salary":  350, "absences": 5, "city": "san francisco" }, { "study_time": 2, "salary": 1600, "absences": 4, "city": "london" }, { "study_time": 3, "salary": 2450, "absences": 3, "city": "paris" }, { "study_time": 4, "salary": 5150, "absences": 5, "city": "san francisco" }, { "study_time": 5, "salary": 5800, "absences": 4, "city": "london" }, { "study_time": 6, "salary": 6050, "absences": 3, "city": "paris" }]

{ "study_time": 13, "salary": ???, "absences": 5, "city": "san francisco" }

x = 0absences_base = 50salary_base = 1000data = []for i in range(50):    if x == 0:        x += 1        data.append({            "study_time": i + 1,            "salary": (i * salary_base + (300 * 2 * (i + 1))) - (5 * absences_base),            "absences": 5,            "city": "san francisco"        })    elif x == 1:        x += 1        data.append({            "study_time": i + 1,            "salary": (i * salary_base + (200 * 2 * (i + 1))) - (4 * absences_base),            "absences": 4,            "city": "london"        })    else:        x = 0        data.append({            "study_time": i + 1,            "salary": (i * salary_base + (100 * 2 * (i + 1))) - (3 * absences_base),            "absences": 3,            "city": "paris"        })for entry in data:    print(entry)

{'study_time': 1, 'salary': 350, 'absences': 5, 'city': 'san francisco'}{'study_time': 2, 'salary': 1600, 'absences': 4, 'city': 'london'}{'study_time': 3, 'salary': 2450, 'absences': 3, 'city': 'paris'}{'study_time': 4, 'salary': 5150, 'absences': 5, 'city': 'san francisco'}{'study_time': 5, 'salary': 5800, 'absences': 4, 'city': 'london'}{'study_time': 6, 'salary': 6050, 'absences': 3, 'city': 'paris'}{'study_time': 7, 'salary': 9950, 'absences': 5, 'city': 'san francisco'}{'study_time': 8, 'salary': 10000, 'absences': 4, 'city': 'london'}{'study_time': 9, 'salary': 9650, 'absences': 3, 'city': 'paris'}{'study_time': 10, 'salary': 14750, 'absences': 5, 'city': 'san francisco'}{'study_time': 11, 'salary': 14200, 'absences': 4, 'city': 'london'}{'study_time': 12, 'salary': 13250, 'absences': 3, 'city': 'paris'}{'study_time': 13, 'salary': 19550, 'absences': 5, 'city': 'san francisco'}

date = [ { "study_time": 1, "salary":  350, "absences": 5, "city": "san francisco" }, { "study_time": 2, "salary": 1600, "absences": 4, "city": "london" }, { "study_time": 3, "salary": 2450, "absences": 3, "city": "paris" }, { "study_time": 4, "salary": 5150, "absences": 5, "city": "san francisco" }, { "study_time": 5, "salary": 5800, "absences": 4, "city": "london" }, { "study_time": 6, "salary": 6050, "absences": 3, "city": "paris" }, {'study_time': 7, 'salary': 9950, 'absences': 5, 'city': 'san francisco'}, {'study_time': 8, 'salary': 10000, 'absences': 4, 'city': 'london'}, {'study_time': 9, 'salary': 9650, 'absences': 3, 'city': 'paris'}]

import pandas as pdimport matplotlib.pyplot as pltfrom sklearn.preprocessing import PolynomialFeaturesfrom sklearn.linear_model import LinearRegressiondata = pd.DataFrame({    "study_time": [1, 2, 3, 4, 5, 6, 7, 8, 9],    "absences": [5, 4, 3, 5, 4, 3, 5, 4, 3],    "San Francisco": [0, 1, 0, 0, 1, 0, 0, 1, 0], # dummy variables    "London": [0, 0, 1, 0, 0, 1, 0, 0, 1], # dummy variables    "Paris": [1, 0, 0, 1, 0, 0, 1, 0, 0], # dummy variables    "salary": [350, 1600, 2450, 5150, 5800, 6050, 9950, 10000, 9650]}) # Independent and dependent variablesX = data[["study_time", "absences", "San Francisco", "London", "Paris"]]y = data["salary"]# Creating polynomial characteristics of degree 2characteristics_2 = PolynomialFeatures(degree=2)x_pol_2 = characteristics_2.fit_transform(X)# Fitting the linear regression modelmodel2 = LinearRegression()model2.fit(x_pol_2, y)# New data provided for predictionnew_data = pd.DataFrame({    "study_time": [13],    "absences": [5],    "San Francisco": [0],    "London": [0],    "Paris": [1]})# Polynomial transformation of the new datanew_data_pol_2 = characteristics_2.transform(new_data)predicted_salary = model2.predict(new_data_pol_2)print("Predicted Salary:", int(predicted_salary[0]) )# Plotplt.subplot(1, 1, 1)plt.scatter(new_data["study_time"], predicted_salary, color='blue', label='Real Salary')plt.scatter(data["study_time"], y, color='blue', label='Real Salary')plt.scatter(data["study_time"], y_pol_2, color='red', label='Polynomial Fit', marker='x')plt.title("Polynomial Regression - Salary and Study Time")plt.xlabel("Study Time")plt.ylabel("Salary")plt.legend()plt.show()