数据源准备
"Time","V1","V2","V3","V4","V5","V6","V7","V8","V9","V10","V11","V12","V13","V14","V15","V16","V17","V18","V19","V20","V21","V22","V23","V24","V25","V26","V27","V28","Amount","Class"
0,-1.3598071336738,-0.0727811733098497,2.53634673796914,1.37815522427443,-0.338320769942518,0.462387777762292,0.239598554061257,0.0986979012610507,0.363786969611213,0.0907941719789316,-0.551599533260813,-0.617800855762348,-0.991389847235408,-0.311169353699879,1.46817697209427,-0.470400525259478,0.207971241929242,0.0257905801985591,0.403992960255733,0.251412098239705,-0.018306777944153,0.277837575558899,-0.110473910188767,0.0669280749146731,0.128539358273528,-0.189114843888824,0.133558376740387,-0.0210530534538215,149.62,"0"
0,1.19185711131486,0.26615071205963,0.16648011335321,0.448154078460911,0.0600176492822243,-0.0823608088155687,-0.0788029833323113,0.0851016549148104,-0.255425128109186,-0.166974414004614,1.61272666105479,1.06523531137287,0.48909501589608,-0.143772296441519,0.635558093258208,0.463917041022171,-0.114804663102346,-0.183361270123994,-0.145783041325259,-0.0690831352230203,-0.225775248033138,-0.638671952771851,0.101288021253234,-0.339846475529127,0.167170404418143,0.125894532368176,-0.00898309914322813,0.0147241691924927,2.69,"0"
1,-1.35835406159823,-1.34016307473609,1.77320934263119,0.379779593034328,-0.503198133318193,1.80049938079263,0.791460956450422,0.247675786588991,-1.51465432260583,0.207642865216696,0.624501459424895,0.066083685268831,0.717292731410831,-0.165945922763554,2.34586494901581,-2.89008319444231,1.10996937869599,-0.121359313195888,-2.26185709530414,0.524979725224404,0.247998153469754,0.771679401917229,0.909412262347719,-0.689280956490685,-0.327641833735251,-0.139096571514147,-0.0553527940384261,-0.0597518405929204,378.66,"0"
1,-0.966271711572087,-0.185226008082898,1.79299333957872,-0.863291275036453,-0.0103088796030823,1.24720316752486,0.23760893977178,0.377435874652262,-1.38702406270197,-0.0549519224713749,-0.226487263835401,0.178228225877303,0.507756869957169,-0.28792374549456,-0.631418117709045,-1.0596472454325,-0.684092786345479,1.96577500349538,-1.2326219700892,-0.208037781160366,-0.108300452035545,0.00527359678253453,-0.190320518742841,-1.17557533186321,0.647376034602038,-0.221928844458407,0.0627228487293033,0.0614576285006353,123.5,"0"
2,-1.15823309349523,0.877736754848451,1.548717846511,0.403033933955121,-0.407193377311653,0.0959214624684256,0.592940745385545,-0.270532677192282,0.817739308235294,0.753074431976354,-0.822842877946363,0.53819555014995,1.3458515932154,-1.11966983471731,0.175121130008994,-0.451449182813529,-0.237033239362776,-0.0381947870352842,0.803486924960175,0.408542360392758,-0.00943069713232919,0.79827849458971,-0.137458079619063,0.141266983824769,-0.206009587619756,0.502292224181569,0.219422229513348,0.215153147499206,69.99,"0"
2,-0.425965884412454,0.960523044882985,1.14110934232219,-0.168252079760302,0.42098688077219,-0.0297275516639742,0.476200948720027,0.260314333074874,-0.56867137571251,-0.371407196834471,1.34126198001957,0.359893837038039,-0.358090652573631,-0.137133700217612,0.517616806555742,0.401725895589603,-0.0581328233640131,0.0686531494425432,-0.0331937877876282,0.0849676720682049,-0.208253514656728,-0.559824796253248,-0.0263976679795373,-0.371426583174346,-0.232793816737034,0.105914779097957,0.253844224739337,0.0810802569229443,3.67,"0"
4,1.22965763450793,0.141003507049326,0.0453707735899449,1.20261273673594,0.191880988597645,0.272708122899098,-0.00515900288250983,0.0812129398830894,0.464959994783886,-0.0992543211289237,-1.41690724314928,-0.153825826253651,-0.75106271556262,0.16737196252175,0.0501435942254188,-0.443586797916727,0.00282051247234708,-0.61198733994012,-0.0455750446637976,-0.21963255278686,-0.167716265815783,-0.270709726172363,-0.154103786809305,-0.780055415004671,0.75013693580659,-0.257236845917139,0.0345074297438413,0.00516776890624916,4.99,"0"
7,-0.644269442348146,1.41796354547385,1.0743803763556,-0.492199018495015,0.948934094764157,0.428118462833089,1.12063135838353,-3.80786423873589,0.615374730667027,1.24937617815176,-0.619467796121913,0.291474353088705,1.75796421396042,-1.32386521970526,0.686132504394383,-0.0761269994382006,-1.2221273453247,-0.358221569869078,0.324504731321494,-0.156741852488285,1.94346533978412,-1.01545470979971,0.057503529867291,-0.649709005559993,-0.415266566234811,-0.0516342969262494,-1.20692108094258,-1.08533918832377,40.8,"0"
7,-0.89428608220282,0.286157196276544,-0.113192212729871,-0.271526130088604,2.6695986595986,3.72181806112751,0.370145127676916,0.851084443200905,-0.392047586798604,-0.410430432848439,-0.705116586646536,-0.110452261733098,-0.286253632470583,0.0743553603016731,-0.328783050303565,-0.210077268148783,-0.499767968800267,0.118764861004217,0.57032816746536,0.0527356691149697,-0.0734251001059225,-0.268091632235551,-0.204232669947878,1.0115918018785,0.373204680146282,-0.384157307702294,0.0117473564581996,0.14240432992147,93.2,"0"
9,-0.33826175242575,1.11959337641566,1.04436655157316,-0.222187276738296,0.49936080649727,-0.24676110061991,0.651583206489972,0.0695385865186387,-0.736727316364109,-0.366845639206541,1.01761446783262,0.836389570307029,1.00684351373408,-0.443522816876142,0.150219101422635,0.739452777052119,-0.540979921943059,0.47667726004282,0.451772964394125,0.203711454727929,-0.246913936910008,-0.633752642406113,-0.12079408408185,-0.385049925313426,-0.0697330460416923,0.0941988339514961,0.246219304619926,0.0830756493473326,3.68,"0"
10,1.44904378114715,-1.17633882535966,0.913859832832795,-1.37566665499943,-1.97138316545323,-0.62915213889734,-1.4232356010359,0.0484558879088564,-1.72040839292037,1.62665905834133,1.1996439495421,-0.671439778462005,-0.513947152539479,-0.0950450453999549,0.230930409124119,0.0319674667862076,0.253414715863197,0.854343814324194,-0.221365413645481,-0.387226474431156,-0.00930189652490052,0.313894410791098,0.0277401580170247,0.500512287104917,0.25136735874921,-0.129477953726618,0.0428498709381461,0.0162532619375515,7.8,"0"
10,0.38497821518095,0.616109459176472,-0.874299702595052,-0.0940186259679115,2.92458437838817,3.31702716826156,0.470454671805879,0.53824722837695,-0.558894612428441,0.30975539423728,-0.259115563735702,-0.326143233995877,-0.0900467227020648,0.362832368569793,0.928903660629178,-0.129486811402759,-0.809978925963589,0.359985390219981,0.70766382644648,0.12599157561542,0.049923685888971,0.238421512225103,0.00912986861262866,0.996710209581086,-0.767314827174801,-0.492208295340017,0.042472441919027,-0.0543373883732122,9.99,"0"
10,1.249998742053,-1.22163680921816,0.383930151282291,-1.23489868766892,-1.48541947377961,-0.753230164566149,-0.689404975426345,-0.227487227519552,-2.09401057344842,1.32372927445937,0.227666231237246,-0.242681998944186,1.20541680770748,-0.317630527025074,0.725674990179153,-0.815612186027305,0.873936447614439,-0.847788598847099,-0.683192626267037,-0.102755941505071,-0.231809239223849,-0.483285330117712,0.0846676908596583,0.392830885335013,0.161134553588505,-0.354990039673962,0.0264155490776107,0.0424220887282304,121.5,"0"
11,1.0693735878819,0.287722129331455,0.828612726634281,2.71252042961718,-0.178398016248009,0.337543730282968,-0.0967168617395962,0.115981735546597,-0.221082566236194,0.460230444301678,-0.773656930526689,0.32338724546722,-0.0110758870883779,-0.178485175177916,-0.65556427824926,-0.19992517131173,0.1240054151819,-0.980496201537345,-0.982916082135047,-0.153197231044512,-0.0368755317335273,0.0744124028162195,-0.0714074332998586,0.104743752596029,0.548264725394119,0.104094153162781,0.0214910583643189,0.021293311477486,27.5,"0"import pandas as pd
import matplotlib.pyplot as plt
import numpy as np输入数据
data = pd.read_csv("creditcard.csv")
data.head()
由于“amount”这一列范围区间较大，待会需要做特殊处理
由于做信用卡欺诈检测这种任务，根据业务特性，很明显会出现样本不均衡的情况，因为大部分信用卡用户都比较正常
其中class=0的为正常值 为1的是异常的
# 计算class=0的有多少个 =1的有多少个
count_classes = pd.value_counts(data['Class'], sort = True).sort_index()
count_classes.plot(kind = 'bar')
plt.title("Fraud class histogram")
plt.xlabel("Class")
plt.ylabel("Frequency")
归一化：“amount”的值可能大于100，而V28却是[-1,1]之间，不做归一化，模型会认为“amount”更重要
# sklearn数据预处理模块做数据预处理
from sklearn.preprocessing import StandardScaler
# sklearn的reshape函数设置-1，即让其自动计算有多少行 得到新的列
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].reshape(-1, 1))
data = data.drop(['Time','Amount'],axis=1)
data.head()
# 取出x值和label值
X = data.ix[:, data.columns != 'Class']
y = data.ix[:, data.columns == 'Class']
# 拿到所有负例的个数和它们的index，用来做过采样
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
# 拿到所有正例的index，如果是做欠采样，那么需要通过index随机取
normal_indices = data[data.Class == 0].index
# 从正例的数据集中采集负例个数的样本
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)
# 转换为numpy的格式
random_normal_indices = np.array(random_normal_indices)
# 合并正例和负例样本
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
# pandas的索引来重新赋值
under_sample_data = data.iloc[under_sample_indices,:]
X_undersample = under_sample_data.ix[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.ix[:, under_sample_data.columns == 'Class']
# Showing ratio
print("Percentage of normal transactions: ", len(under_sample_data[under_sample_data.Class == 0])/len(under_sample_data))
print("Percentage of fraud transactions: ", len(under_sample_data[under_sample_data.Class == 1])/len(under_sample_data))
print("Total number of transactions in resampled data: ", len(under_sample_data))打印下采样后的样本个数 输出
Percentage of normal transactions: 0.5
Percentage of fraud transactions: 0.5
Total number of transactions in resampled data: 984交叉验证：
from sklearn.cross_validation import train_test_split
# 原始数据集切分 random_state 为洗牌随机切分 -- 切分后的验证集可以用于验证下采样的模型好坏
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.3, random_state = 0)
print("Number transactions train dataset: ", len(X_train))
print("Number transactions test dataset: ", len(X_test))
print("Total number of transactions: ", len(X_train)+len(X_test))
# 下采样数据集切分
X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = train_test_split(X_undersample
,y_undersample
,test_size = 0.3
,random_state = 0)
print("")
print("Number transactions train dataset: ", len(X_train_undersample))
print("Number transactions test dataset: ", len(X_test_undersample))
print("Total number of transactions: ", len(X_train_undersample)+len(X_test_undersample))输出结果
Number transactions train dataset: 199364
Number transactions test dataset: 85443
Total number of transactions: 284807
Number transactions train dataset: 688
Number transactions test dataset: 296
Total number of transactions: 984模型的评估方法–样本极度不均衡，精度是会骗人的，用recall更好
#Recall = TP/(TP+FN)
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold, cross_val_score
from sklearn.metrics import confusion_matrix,recall_score,classification_report 正则化惩罚 – 惩罚权重参数
def printing_Kfold_scores(x_train_data,y_train_data):
# 5折交叉验证
fold = KFold(len(y_train_data),5,shuffle=False)
# 由于不知道具体的C值 这里几个先验值逐一试试
c_param_range = [0.01,0.1,1,10,100]
results_table = pd.DataFrame(index = range(len(c_param_range),2), columns = ['C_parameter','Mean recall score'])
results_table['C_parameter'] = c_param_range
# the k-fold will give 2 lists: train_indices = indices[0], test_indices = indices[1]
j = 0
for c_param in c_param_range:
print('-------------------------------------------')
print('C parameter: ', c_param)
print('-------------------------------------------')
print('')
# sklearn KFold交叉验证分组情况样本
recall_accs = []
for iteration, indices in enumerate(fold,start=1):
# 正则化选择参数：penalty 优化算法选择参数：solver 分类方式选择参数：multi_class 类型权重参数： class_weight 样本权重参数： sample_weight
lr = LogisticRegression(C = c_param, penalty = 'l1')
# Use the training data to fit the model. In this case, we use the portion of the fold to train the model
# with indices[0]. We then predict on the portion assigned as the 'test cross validation' with indices[1]
# iloc比较简单，它是基于索引位来选取数据集，0:4就是选取 0，1，2，3这四行
lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
# 获取预测值
y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)
# Calculate the recall score and append it to a list for recall scores representing the current c_parameter
recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)
recall_accs.append(recall_acc)
print('Iteration ', iteration,': recall score = ', recall_acc)
# The mean value of those recall scores is the metric we want to save and get hold of.
results_table.ix[j,'Mean recall score'] = np.mean(recall_accs)
j += 1
print('')
print('Mean recall score ', np.mean(recall_accs))
print('')
best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']
# Finally, we can check which C parameter is the best amongst the chosen.
print('*********************************************************************************')
print('Best model to choose from cross validation is with C parameter = ', best_c)
print('*********************************************************************************')
return best_c输入结果
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)输出结果
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.958904109589
Iteration 2 : recall score = 0.917808219178
Iteration 3 : recall score = 1.0
Iteration 4 : recall score = 0.972972972973
Iteration 5 : recall score = 0.954545454545
Mean recall score 0.960846151257
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.835616438356
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.915254237288
Iteration 4 : recall score = 0.932432432432
Iteration 5 : recall score = 0.878787878788
Mean recall score 0.885020937099
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.835616438356
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.945945945946
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.900923434357
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.849315068493
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.959459459459
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.906365863087
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.86301369863
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.959459459459
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.909105589115
*********************************************************************************
Best model to choose from cross validation is with C parameter = 0.01
*********************************************************************************def plot_confusion_matrix(cm, classes,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=0)
plt.yticks(tick_marks, classes)
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')import itertools
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample = lr.predict(X_test_undersample.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_pred_undersample)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = lr.predict(X_test.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test,y_pred)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
best_c = printing_Kfold_scores(X_train,y_train)原始数据集的召回率远远低于下采样数据集的召回率
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.492537313433
Iteration 2 : recall score = 0.602739726027
Iteration 3 : recall score = 0.683333333333
Iteration 4 : recall score = 0.569230769231
Iteration 5 : recall score = 0.45
Mean recall score 0.559568228405
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.567164179104
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.683333333333
Iteration 4 : recall score = 0.584615384615
Iteration 5 : recall score = 0.525
Mean recall score 0.595310250644
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.716666666667
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.5625
Mean recall score 0.612645688837
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.733333333333
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.575
Mean recall score 0.61847902217
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.733333333333
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.575
Mean recall score 0.61847902217
*********************************************************************************
Best model to choose from cross validation is with C parameter = 10.0
*********************************************************************************lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train,y_train.values.ravel())
y_pred_undersample = lr.predict(X_test.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test,y_pred_undersample)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
lr = LogisticRegression(C = 0.01, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample_proba = lr.predict_proba(X_test_undersample.values)
thresholds = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
plt.figure(figsize=(10,10))
j = 1
for i in thresholds:
y_test_predictions_high_recall = y_pred_undersample_proba[:,1] > i
plt.subplot(3,3,j)
j += 1
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_test_predictions_high_recall)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Threshold >= %s'%i) 输出
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 1.0
Recall metric in the testing dataset: 0.986394557823
Recall metric in the testing dataset: 0.931972789116
Recall metric in the testing dataset: 0.884353741497
Recall metric in the testing dataset: 0.836734693878
Recall metric in the testing dataset: 0.748299319728
Recall metric in the testing dataset: 0.571428571429
import pandas as pd
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_splitcredit_cards=pd.read_csv('creditcard.csv')
columns=credit_cards.columns
# The labels are in the last column ('Class'). Simply remove it to obtain features columns
features_columns=columns.delete(len(columns)-1)
features=credit_cards[features_columns]
labels=credit_cards['Class']features_train, features_test, labels_train, labels_test = train_test_split(features,
labels,
test_size=0.2,
random_state=0)过采样算法
下采样可能导致较高的误杀率 过采样效果更好
（https://blog.csdn.net/keycoder/article/details/79188853）
* 1、对于少数类中每一个样本x，以欧氏距离为标准计算它到少数类样本集中所有样本的距离，得到其k近邻。
2、根据样本不平衡比例设置一个采样比例以确定采样倍率N，对于每一个少数类样本x，从其k近邻中随机选择若干个样本，假设选择的近邻为xn。
3、对于每一个随机选出的近邻xn，分别与原样本按照如下的公式构建新的样本
xnew=x+rand(0,1)∗|x−xn|
oversampler=SMOTE(random_state=0)
os_features,os_labels=oversampler.fit_sample(features_train,labels_train)len(os_labels[os_labels==1])输出结果
227454os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)输出结果
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.968861347792
Iteration 4 : recall score = 0.957595541926
Iteration 5 : recall score = 0.958430881173
Mean recall score 0.933989438728
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970410534469
Iteration 4 : recall score = 0.959980655302
Iteration 5 : recall score = 0.960178498807
Mean recall score 0.935125822266
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970454796946
Iteration 4 : recall score = 0.96014552489
Iteration 5 : recall score = 0.960596168431
Mean recall score 0.935251182603
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.97065397809
Iteration 4 : recall score = 0.960343368396
Iteration 5 : recall score = 0.960530220596
Mean recall score 0.935317397966
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970543321899
Iteration 4 : recall score = 0.960211472725
Iteration 5 : recall score = 0.960903924995
Mean recall score 0.935343628474
*********************************************************************************
Best model to choose from cross validation is with C parameter = 100.0
*********************************************************************************lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(os_features,os_labels.values.ravel())
y_pred = lr.predict(features_test.values)
# Compute confusion matrix
cnf_matrix = confusion_matrix(labels_test,y_pred)
np.set_printoptions(precision=2)
print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()