我已经能够成功地使用SVR来预测具有一个数据条目的数据集的值。但是，我的数据集每个“行”或“条目”有47个条目，或者您想要调用它。我上传了我的数据集csv，在我的代码中，我已经在get_data函数中注释掉了其他46个条目。
所有47个数据条目都是相对和影响x，即玩家的工资。我试图在玩家的工资知晓之前仅使用玩家可用的统计数据来预测玩家的未来薪水。但是，正如我所提到的，很多统计数据定义了薪水，目前我只能对1个统计数据进行预测。
import csv
import numpy as np
from sklearn.svm import SVR
import matplotlib.pyplot as plt
salary = []
stats = []
def get_data(filename):
with open(filename, 'r', encoding='utf8', errors='ignore') as csvfile:
csvFileReader = csv.reader(csvfile)
for row in csvFileReader:
# stats.append(float(row[4])) #
# stats.append(int(row[5])) #
salary.append(float(row[6]))
# stats.append(int(row[8])) #
# stats.append(int(row[9])) #
# stats.append(int(row[10])) #
stats.append(int(row[11])) #
# stats.append(int(row[12])) #
# stats.append(int(row[13])) #
# stats.append(float(row[14])) #
# stats.append(int(row[15])) #
# stats.append(int(row[16])) #
# stats.append(int(row[17])) #
# stats.append(int(row[18])) #
# stats.append(int(row[19])) #
# stats.append(int(row[20])) #
# stats.append(int(row[21])) #
# stats.append(int(row[22])) #
# stats.append(int(row[23])) #
# stats.append(int(row[24])) #
# stats.append(float(row[25])) #
# stats.append(int(row[26])) #
# stats.append(int(row[27])) #
# stats.append(int(row[28])) #
# stats.append(int(row[29])) #
# stats.append(int(row[30])) #
# stats.append(int(row[31])) #
# stats.append(int(row[32])) #
# stats.append(int(row[33])) #
# stats.append(int(row[34])) #
# stats.append(int(row[35])) #
# stats.append(float(row[36])) #
# stats.append(int(row[37])) #
# stats.append(int(row[38])) #
# stats.append(int(row[39])) #
# stats.append(int(row[40])) #
# stats.append(int(row[41])) #
# stats.append(int(row[42])) #
# stats.append(int(row[43])) #
# stats.append(int(row[44])) #
# stats.append(int(row[45])) #
# stats.append(int(row[46])) #
# stats.append(float(row[47])) #
# stats.append(int(row[48])) #
# stats.append(int(row[49])) #
# stats.append(int(row[50])) #
# stats.append(int(row[51])) #
# stats.append(int(row[52])) #
return
get_data('dataset.csv')
def predict_salary(stats, salary, x):
stats = np.reshape(stats,(len(salary), int(len(stats)/len(salary))))
svr_lin = SVR(kernel='linear', C=1e3, epsilon=0.2, cache_size=7000)
svr_rbf = SVR(kernel= 'rbf', C=1e3, gamma=0.1, cache_size=7000)
svr_poly = SVR(kernel='poly', C=1e3, degree=2, cache_size=7000)
svr_lin.fit(stats, salary)
svr_rbf.fit(stats, salary)
svr_poly.fit(stats, salary)
plt.scatter(stats, salary, color='black', label='Data')
plt.plot(stats, svr_lin.predict(stats), color='green', label='Linear model')
plt.plot(stats, svr_rbf.predict(stats), color='red', label='RBF model')
plt.plot(stats, svr_poly.predict(stats), color='blue', label='Polynomial model')
plt.xlabel('Stats')
plt.ylabel('Salary')
plt.title('Support Vector Regression')
plt.legend()
plt.show()
return svr_lin.predict(x)[0], svr_rbf.predict(x)[0], svr_poly.predict(x)[0]
projected_salary = predict_salary(stats, salary, 1)
print (projected_salary)
这里是dataset.csv，我只包含了10行，但我拥有最多200行数据：
N/A,N/A,player 1,team,3,26,1350000,508500,22,31,32,8,361,3,0.217,0,0,0,0,25,33,48,11,390,13,0.256,0,0,0,0,9,18,22,1,225,4,0.215,0,0,0,0,22,27,37,8,313,9,0.192,0,0,0,0,0
N/A,N/A,player 2,team,3,27,805000,508500,15,26,17,4,176,1,0.242,0,0,0,0,0,0,0,0,2,0,0,0,0,0,0,1,1,2,0,13,0,0.231,0,0,0,0,10,10,17,1,168,1,0.201,0,0,0,0,0
N/A,N/A,player 3,team,3,25,2625000,508500,25,17,69,3,460,58,0.26,0,0,0,0,15,28,56,4,454,57,0.226,0,0,0,0,39,48,72,6,611,56,0.25,0,0,0,0,2,1,9,0,22,13,0.368,2,0,0,0,0
N/A,N/A,player 4,team,3,26,3575000,508500,65,81,73,30,601,6,0.243,0,0,0,0,37,46,44,11,497,13,0.258,0,0,0,0,29,36,47,10,411,4,0.221,0,0,0,1,25,36,41,8,335,5,0.265,0,0,0,0,0
N/A,N/A,player 5,team,3,28,1950000,508500,23,34,45,7,324,4,0.255,0,0,0,0,35,45,56,2,509,8,0.28,1,0,0,0,32,29,68,4,492,12,0.281,0,0,0,0,5,14,15,0,144,1,0.25,0,0,0,0,0
N/A,N/A,player 6,team,2.5,30,700000,508500,3,0,7,0,141,0,0.174,0,0,0,0,28,49,38,11,355,0,0.234,0,0,0,0,18,28,22,9,275,0,0.207,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
N/A,N/A,player 7,team,2.5,26,2550000,508500,31,39,67,6,622,17,0.294,1,0,0,0,25,35,57,1,452,19,0.272,0,0,0,0,3,4,13,1,125,1,0.237,0,0,0,0,5,10,17,0,131,0,0.289,0,0,0,0,0
N/A,N/A,player 8,team,3,28,938000,508500,15,28,21,6,166,4,0.284,0,0,0,0,8,10,13,2,113,0,0.146,0,0,0,0,3,4,8,0,79,1,0.213,0,0,0,0,11,19,16,4,197,0,0.189,0,0,0,0,0
N/A,N/A,player 9,team,3,24,2300000,508500,40,49,52,5,466,21,0.277,0,0,0,0,36,43,59,4,552,16,0.227,0,0,0,0,27,26,34,6,332,8,0.261,0,0,0,0,5,5,5,0,61,2,0.291,0,0,0,0,0
N/A,N/A,player 10,team,3,27,3025000,508500,63,70,57,24,548,0,0.245,0,0,0,0,30,31,30,10,234,0,0.304,0,0,0,0,57,76,74,24,478,8,0.312,0,0,0,0,23,17,32,5,213,2,0.263,0,0,0,0,0
我花了几天的时间才使用47个条目中的一个来完成这个工作，还有几个试图找出如何让它来分析每个玩家的整个集合。我是python的初学者，没有统计背景，所以我现在完全迷失了！感谢任何帮助或指导，谢谢！
答案 0 :(得分：0)
我会使用pandas，因为至少可以说，通过评论线条所采用的方法是痛苦的。
import pandas
# list of columns (features) you'd like to use
columns_of_interest = [11, 15, 20, 26] # features you'd like to use (stats). You only used 11 but you could use many more
df = pandas.read_csv(filename, header=None)
stats = df[df[columns_of_interest]].values # select columns of interest
salary = df[6].values # salary column, which is in column 6
然后，您可以使用sklearn的train_test_split。这将使您能够将数据拆分为培训和测试。
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(stats, salary)
您可以将其发送到预测功能：
pred_lin, pred_rbf, pred_poly = predict_salary(x_train, y_train, x_test)
我添加了三个参数，因为函数返回三组预测，每组都来自每个SVR模型。
另外，我只想将函数的return更改为：
svr_lin.predict(x), svr_rbf.predict(x), svr_poly.predict(x)
这将返回测试集中的整个预测集。
import csv
import numpy as np
from sklearn.svm import SVR
import matplotlib.pyplot as plt
import pandas
from sklearn.model_selection import train_test_split
def predict_salary(stats, salary, x):
svr_lin = SVR(kernel='linear', C=1e3, epsilon=0.2, cache_size=7000)
svr_rbf = SVR(kernel= 'rbf', C=1e3, gamma=0.1, cache_size=7000)
svr_poly = SVR(kernel='poly', C=1e3, degree=2, cache_size=7000)
svr_lin.fit(stats, salary)
svr_rbf.fit(stats, salary)
svr_poly.fit(stats, salary)
# plt.scatter(stats, salary, color='black', label='Data')
plt.scatter(salary, svr_lin.predict(stats), color='green', label='Linear model')
plt.scatter(salary, svr_rbf.predict(stats), color='red', label='RBF model')
plt.scatter(salary, svr_poly.predict(stats), color='blue', label='Polynomial model')
plt.xlabel('Actual Salary')
plt.ylabel('Salary Predictions')
plt.title('Support Vector Regression')
plt.legend()
plt.show()
return svr_lin.predict(x), svr_rbf.predict(x), svr_poly.predict(x)
filename = '/Users/carlomazzaferro/Desktop/p.csv'
columns_of_interest = [11, 15, 20, 26]
df = pandas.read_csv(filename, header=None)
stats = df[columns_of_interest].values # select columns of interest
salary = df[6].values # salary column, which is in column
x_train, x_test, y_train, y_test = train_test_split(stats, salary)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
pred_lin, pred_rbf, pred_poly = predict_salary(x_train, y_train, x_test)