敏捷数据科学 - 提高预测性能

在本章中，我们将重点构建一个模型，该模型有助于预测学生的表现，其中包含许多属性。 重点展示学生考试不及格结果。

流程

考核目标值为G3。 该值可以被分类并进一步分类为失败和成功。 如果G3值大于或等于10，则学生通过考试。

示例

考虑以下示例，其中执行代码来预测学生的表现 −

import pandas as pd
""" Read data file as DataFrame """
df = pd.read_csv("student-mat.csv", sep=";")
""" Import ML helpers """
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import GridSearchCV, cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.svm import LinearSVC # Support Vector Machine Classifier model
""" Split Data into Training and Testing Sets """
def split_data(X, Y):
 return train_test_split(X, Y, test_size=0.2, random_state=17)
""" Confusion Matrix """
def confuse(y_true, y_pred):
 cm = confusion_matrix(y_true=y_true, y_pred=y_pred)
 # print("
Confusion Matrix: 
", cm)
  fpr(cm)
 ffr(cm)
""" False Pass Rate """
def fpr(confusion_matrix):
 fp = confusion_matrix[0][1]
 tf = confusion_matrix[0][0]
 rate = float(fp) / (fp + tf)
 print("False Pass Rate: ", rate)
""" False Fail Rate """
def ffr(confusion_matrix):
 ff = confusion_matrix[1][0]
 tp = confusion_matrix[1][1]
 rate = float(ff) / (ff + tp)
 print("False Fail Rate: ", rate)
 return rate
""" Train Model and Print Score """
def train_and_score(X, y):
 X_train, X_test, y_train, y_test = split_data(X, y)
 clf = Pipeline([
 ('reduce_dim', SelectKBest(chi2, k=2)),
 ('train', LinearSVC(C=100))
 ])
 scores = cross_val_score(clf, X_train, y_train, cv=5, n_jobs=2)
 print("Mean Model Accuracy:", np.array(scores).mean())
 clf.fit(X_train, y_train)
 confuse(y_test, clf.predict(X_test))
 print()
""" Main Program """
def main():
 print("
Student Performance Prediction")
 # For each feature, encode to categorical values
 class_le = LabelEncoder()
 for column in df[["school", "sex", "address", "famsize", "Pstatus", "Mjob",
"Fjob", "reason", "guardian", "schoolsup", "famsup", "paid", "activities",
"nursery", "higher", "internet", "romantic"]].columns:
 df[column] = class_le.fit_transform(df[column].values)
 # Encode G1, G2, G3 as pass or fail binary values
 for i, row in df.iterrows():
 if row["G1"] >= 10:
 df["G1"][i] = 1
 else:
 df["G1"][i] = 0
 if row["G2"] >= 10:
 df["G2"][i] = 1
 else:
 df["G2"][i] = 0
 if row["G3"] >= 10:
 df["G3"][i] = 1
 else:
 df["G3"][i] = 0
 # Target values are G3
 y = df.pop("G3")
 # Feature set is remaining features
 X = df
 print("

Model Accuracy Knowing G1 & G2 Scores")
 print("=====================================")
 train_and_score(X, y)
 # Remove grade report 2
 X.drop(["G2"], axis = 1, inplace=True)
 print("

Model Accuracy Knowing Only G1 Score")
 print("=====================================")
 train_and_score(X, y)
 # Remove grade report 1
 X.drop(["G1"], axis=1, inplace=True)
 print("

Model Accuracy Without Knowing Scores")
 print("=====================================")
 train_and_score(X, y)
main()

输出

上面的代码生成的输出如下所示

仅参考一个变量来处理预测。 参考一个变量，学生成绩预测如下:−