kaggle研究生招生（中）

上次将数据训练了模型

由于数据中的大多数候选人都有70%以上的机会，许多不成功的候选人都没有很好的预测。

df["Chance of Admit"].plot(kind = 'hist',bins = 200,figsize = (6,6))
plt.title("Chance of Admit")
plt.xlabel("Chance of Admit")
plt.ylabel("Frequency")
plt.show()

为分类准备数据

如果候选人的录取机会大于80%，则该候选人将获得1个标签。
如果候选人的录取机会小于或等于80%，则该候选人将获得0标签。

# reading the dataset
df = pd.read_csv("../input/Admission_Predict.csv",sep = ",")

# it may be needed in the future.
serialNo = df["Serial No."].values
df.drop(["Serial No."],axis=1,inplace = True)

y = df["Chance of Admit"].values
x = df.drop(["Chance of Admit"],axis=1)

# separating train (80%) and test (%20) sets
from sklearn.model_selection import train_test_split
x_train, x_test,y_train, y_test = train_test_split(x,y,test_size = 0.20,random_state = 42)

# normalization
from sklearn.preprocessing import MinMaxScaler
scalerX = MinMaxScaler(feature_range=(0, 1))
x_train[x_train.columns] = scalerX.fit_transform(x_train[x_train.columns])
x_test[x_test.columns] = scalerX.transform(x_test[x_test.columns])

y_train_01 = [1 if each > 0.8 else 0 for each in y_train]
y_test_01  = [1 if each > 0.8 else 0 for each in y_test]

# list to array
y_train_01 = np.array(y_train_01)
y_test_01 = np.array(y_test_01)

逻辑回归

from sklearn.linear_model import LogisticRegression
lrc = LogisticRegression()
lrc.fit(x_train,y_train_01)
print("score: ", lrc.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(lrc.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(lrc.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_lrc = confusion_matrix(y_test_01,lrc.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29

# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_lrc,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,lrc.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,lrc.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,lrc.predict(x_test)))

score: 0.9
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9565217391304348
recall_score: 0.7586206896551724
f1_score: 0.8461538461538461

Test for Train Dataset:

cm_lrc_train = confusion_matrix(y_train_01,lrc.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_lrc_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

SVC

from sklearn.svm import SVC
svm = SVC(random_state = 1)
svm.fit(x_train,y_train_01)
print("score: ", svm.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(svm.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(svm.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_svm = confusion_matrix(y_test_01,svm.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29

# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_svm,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,svm.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,svm.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,svm.predict(x_test)))

score: 0.9
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9565217391304348
recall_score: 0.7586206896551724
f1_score: 0.8461538461538461

Test for Train Dataset

cm_svm_train = confusion_matrix(y_train_01,svm.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_svm_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

朴素贝叶斯

from sklearn.naive_bayes import GaussianNB
nb = GaussianNB()
nb.fit(x_train,y_train_01)
print("score: ", nb.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(nb.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(nb.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_nb = confusion_matrix(y_test_01,nb.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29
# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_nb,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,nb.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,nb.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,nb.predict(x_test)))

score: 0.9625
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9333333333333333
recall_score: 0.9655172413793104
f1_score: 0.9491525423728815

Test for Train Dataset:

cm_nb_train = confusion_matrix(y_train_01,nb.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_nb_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

决策树

from sklearn.tree import DecisionTreeClassifier
dtc = DecisionTreeClassifier()
dtc.fit(x_train,y_train_01)
print("score: ", dtc.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(dtc.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(dtc.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_dtc = confusion_matrix(y_test_01,dtc.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29

# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_dtc,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,dtc.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,dtc.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,dtc.predict(x_test)))

score: 0.9375
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9615384615384616
recall_score: 0.8620689655172413
f1_score: 0.9090909090909091

Test for Train Dataset

cm_dtc_train = confusion_matrix(y_train_01,dtc.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_dtc_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

随机森林

from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier(n_estimators = 100,random_state = 1)
rfc.fit(x_train,y_train_01)
print("score: ", rfc.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(rfc.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(rfc.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_rfc = confusion_matrix(y_test_01,rfc.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29
# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_rfc,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,rfc.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,rfc.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,rfc.predict(x_test)))

score: 0.9375
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9615384615384616
recall_score: 0.8620689655172413
f1_score: 0.9090909090909091

Test for Train Dataset

cm_rfc_train = confusion_matrix(y_train_01,rfc.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_rfc_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

kNN

from sklearn.neighbors import KNeighborsClassifier

# finding k value
scores = []
for each in range(1,50):
    knn_n = KNeighborsClassifier(n_neighbors = each)
    knn_n.fit(x_train,y_train_01)
    scores.append(knn_n.score(x_test,y_test_01))
    
plt.plot(range(1,50),scores)
plt.xlabel("k")
plt.ylabel("accuracy")
plt.show()

knn = KNeighborsClassifier(n_neighbors = 3) # n_neighbors = k
knn.fit(x_train,y_train_01)
print("score of 3 :",knn.score(x_test,y_test_01))
print("real value of y_test_01[1]: " + str(y_test_01[1]) + " -> the predict: " + str(knn.predict(x_test.iloc[[1],:])))
print("real value of y_test_01[2]: " + str(y_test_01[2]) + " -> the predict: " + str(knn.predict(x_test.iloc[[2],:])))

# confusion matrix
from sklearn.metrics import confusion_matrix
cm_knn = confusion_matrix(y_test_01,knn.predict(x_test))
# print("y_test_01 == 1 :" + str(len(y_test_01[y_test_01==1]))) # 29

# cm visualization
import seaborn as sns
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_knn,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.title("Test for Test Dataset")
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.show()

from sklearn.metrics import precision_score, recall_score
print("precision_score: ", precision_score(y_test_01,knn.predict(x_test)))
print("recall_score: ", recall_score(y_test_01,knn.predict(x_test)))

from sklearn.metrics import f1_score
print("f1_score: ",f1_score(y_test_01,knn.predict(x_test)))

score of 3 : 0.9375
real value of y_test_01[1]: 0 -> the predict: [0]
real value of y_test_01[2]: 1 -> the predict: [1]

precision_score: 0.9285714285714286
recall_score: 0.896551724137931
f1_score: 0.912280701754386

Test for Train Dataset:

cm_knn_train = confusion_matrix(y_train_01,knn.predict(x_train))
f, ax = plt.subplots(figsize =(5,5))
sns.heatmap(cm_knn_train,annot = True,linewidths=0.5,linecolor="red",fmt = ".0f",ax=ax)
plt.xlabel("predicted y values")
plt.ylabel("real y values")
plt.title("Test for Train Dataset")
plt.show()

所有分类算法都取得了大约90%的成功。最成功的是高斯朴素贝叶斯，得分为96%。

y = np.array([lrc.score(x_test,y_test_01),svm.score(x_test,y_test_01),nb.score(x_test,y_test_01),dtc.score(x_test,y_test_01),rfc.score(x_test,y_test_01),knn.score(x_test,y_test_01)])
#x = ["LogisticRegression","SVM","GaussianNB","DecisionTreeClassifier","RandomForestClassifier","KNeighborsClassifier"]
x = ["LogisticReg.","SVM","GNB","Dec.Tree","Ran.Forest","KNN"]

plt.bar(x,y)
plt.title("Comparison of Classification Algorithms")
plt.xlabel("Classfication")
plt.ylabel("Score")
plt.show()

上文是回归算法，此文分类