{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport cv2","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#pip install dicom","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import dicom\nimport os\nimport numpy\nfrom matplotlib import pyplot, cm\n#%pylab inline","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#im = cv2.imread('../input/siim-isic-melanoma-classification/jpeg/train/ISIC_0077735.jpg')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#hog = cv2.HOGDescriptor()\n#winSize = (64,64)\n#blockSize = (16,16)\n#blockStride = (8,8)\n#cellSize = (8,8)\n#nbins = 9\n#derivAperture = 1\n#winSigma = 4.\n#histogramNormType = 0\n#L2HysThreshold = 2.0000000000000001e-01\n#gammaCorrection = 0\n#nlevels = 64\n#hog = cv2.HOGDescriptor(winSize,blockSize,blockStride,cellSize,nbins,derivAperture,winSigma,\n#                        histogramNormType,L2HysThreshold,gammaCorrection,nlevels)\n#compute(img[, winStride[, padding[, locations]]]) -> descriptors\n#winStride = (8,8)\n#padding = (8,8)\n#locations = ((10,20),)\n#hist = hog.compute(im,winStride,padding,locations)\n#print (hist)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#lists = []\n#for i in range(hist.shape[0]):\n#    lists.append([])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print (lists[0], lists[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#for i in range(hist.shape[0]):\n#    lists[i].append(hist[i][0])\n#    print (i, hist[i][0], lists[i], '\\n')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import glob\n#import os\n#lst1 = []\n#j = 0\n\n#for filepath in glob.iglob('../input/siim-isic-melanoma-classification/jpeg/train/*.jpg'):\n#    lst1.append(os.path.basename(filepath))\n#    print (j , os.path.basename(filepath))\n#    j = j + 1\n#    im = cv2.imread(filepath)\n#    hist = hog.compute(im,winStride,padding,locations)\n#    for i in range(hist.shape[0]):\n#        lists[i].append(hist[i][0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#lists[0][0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#lists[0][1]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#df = pd.DataFrame(list(zip(lst1, lists))) \n#print (df.head())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#df.to_csv(\"train_jpg1.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#df.to_csv(\"train_jpg2.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_hog = pd.read_csv('../input/hogtrain-1/train_jpg1.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_hog.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import glob\nimport os\nlst_1 = []\nfor filepath in glob.iglob('../input/siim-isic-melanoma-classification/jpeg/train/*.jpg'):\n    lst_1.append(os.path.basename(filepath))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2 = pd.DataFrame(lst_1)\ndf_2.head()\ndf_2.to_csv(\"train_filenames.csv\", index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for m in range(len(train_hog)):\n    x = train_hog['1'][m].split(',')\n    for k in range(len(x)):\n        x[k] = x[k].replace(']', '')\n        x[k] = float(x[k].replace('[', ''))\n    df_2 = pd.concat([df_2, pd.DataFrame(x)], axis=1)\ndf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.to_csv(\"train_jpg_3.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.columns = ['feature'+str(j) for j in range(df_2.shape[1])]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.rename(columns={'feature0':'image_name'}, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for l in range(len(df_2)):\n    df_2[\"image_name\"][l]= df_2[\"image_name\"][l].replace(\".jpg\", \"\")\ndf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com = train.copy()\ntrain_com.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1 = train_com.merge(df_2, on='image_name', how='left')\ntrain_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.to_csv(\"train_jpg_4.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.loc[train_com_1['sex'] == 'female', 'sex'] = 0\ntrain_com_1.loc[train_com_1['sex'] == 'male', 'sex'] = 1\ntrain_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1['sex'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"null_columns=train_com_1.columns[train_com_1.isnull().any()]\ntrain_com_1[null_columns].isnull().sum()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1['sex'] = train_com_1['sex'].fillna(1)\ntrain_com_1['sex'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1['age_approx'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.loc[train_com_1['age_approx'] == 0.0, 'age_approx'] = train_com_1['age_approx'].mean()\ntrain_com_1['age_approx'] = train_com_1['age_approx'].fillna(train_com_1['age_approx'].mean())\ntrain_com_1['age_approx'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1['anatom_site_general_challenge'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'torso', 'anatom_site_general_challenge'] = 0\ntrain_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'lower extremity', 'anatom_site_general_challenge'] = 1\ntrain_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'upper extremity', 'anatom_site_general_challenge'] = 2\ntrain_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'head/neck', 'anatom_site_general_challenge'] = 3\ntrain_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'palms/soles', 'anatom_site_general_challenge'] = 4\ntrain_com_1.loc[train_com_1['anatom_site_general_challenge'] == 'oral/genital', 'anatom_site_general_challenge'] = 5\ntrain_com_1['anatom_site_general_challenge'] = train_com_1['anatom_site_general_challenge'].fillna(0)\ntrain_com_1['anatom_site_general_challenge'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1['diagnosis'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.drop(['image_name', 'patient_id', 'diagnosis', 'benign_malignant'], axis=1, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_com_1.to_csv(\"m_train.csv\", index= False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_features = train_com_1.loc[:, train_com_1.columns != 'target']\ntrain_features.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = train_com_1.loc[:, train_com_1.columns == 'target']\ntrain_labels.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_val, y_train, y_val = train_test_split(train_features, train_labels, test_size=0.1)\nprint (X_train.shape, y_train.shape)\nprint (X_val.shape, y_val.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Import the model we are using\n#from sklearn.ensemble import RandomForestClassifier\n# Instantiate model with 1000 decision trees\n#rf = RandomForestClassifier(n_estimators = 1000, random_state = 42)\n# Train the model on training data\n#rf.fit(X_train, y_train);\n# Use the forest's predict method on the test data\n#predictions = rf.predict(X_val)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#predictions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Confusion Matrix\n#from sklearn.metrics import confusion_matrix\n#cm = confusion_matrix(y_val, predictions)\n#print (cm)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Accuracy\n#from sklearn.metrics import accuracy_score\n#acc = accuracy_score(y_val, predictions)\n#print (acc)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Recall\n#from sklearn.metrics import recall_score\n#rec = recall_score(y_val, predictions, average=None)\n#print (rec)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Precision\n#from sklearn.metrics import precision_score\n#prec = precision_score(y_val, predictions, average=None)\n#print (prec)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#from sklearn.metrics import f1_score\n#f1 = f1_score(y_val, predictions, average=None)\n#print (f1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#im = cv2.imread('../input/siim-isic-melanoma-classification/jpeg/test/ISIC_0092481.jpg')\n#hog = cv2.HOGDescriptor()\n#winSize = (64,64)\n#blockSize = (16,16)\n#blockStride = (8,8)\n#cellSize = (8,8)\n#nbins = 9\n#derivAperture = 1\n#winSigma = 4.\n#histogramNormType = 0\n#L2HysThreshold = 2.0000000000000001e-01\n#gammaCorrection = 0\n#nlevels = 64\n#hog = cv2.HOGDescriptor(winSize,blockSize,blockStride,cellSize,nbins,derivAperture,winSigma,\n#                        histogramNormType,L2HysThreshold,gammaCorrection,nlevels)\n#compute(img[, winStride[, padding[, locations]]]) -> descriptors\n#winStride = (8,8)\n#padding = (8,8)\n#locations = ((10,20),)\n#hist = hog.compute(im,winStride,padding,locations)\n#print (hist)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_lists = []\n#for i in range(hist.shape[0]):\n#    test_lists.append([])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#for i in range(hist.shape[0]):\n#    test_lists[i].append(hist[i][0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import glob\n#import os\n#testlst1 = []\n#j = 0\n\n#for filepath in glob.iglob('../input/siim-isic-melanoma-classification/jpeg/test/*.jpg'):\n#    testlst1.append(os.path.basename(filepath))\n#    print (j , os.path.basename(filepath))\n#    j = j + 1\n#    im = cv2.imread(filepath)\n#    hist = hog.compute(im,winStride,padding,locations)\n#    for i in range(hist.shape[0]):\n#        test_lists[i].append(hist[i][0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf = pd.DataFrame(list(zip(testlst1, test_lists))) \n#print (tdf.head())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf.to_csv(\"test_jpg1.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_hog = pd.read_csv('../input/test-hog/test_jpg1.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import glob\n#import os\n#test_lst_1 = []\n#for filepath in glob.iglob('../input/siim-isic-melanoma-classification/jpeg/test/*.jpg'):\n#    test_lst_1.append(os.path.basename(filepath))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf_2 = pd.DataFrame(test_lst_1)\n#tdf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#for m in range(len(test_hog)):\n#    x = test_hog['1'][m].split(',')\n#    for k in range(len(x)):\n#        x[k] = x[k].replace(']', '')\n#        x[k] = float(x[k].replace('[', ''))\n#    tdf_2 = pd.concat([tdf_2, pd.DataFrame(x)], axis=1)\n#tdf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf_2.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf_2.columns = ['feature'+str(j) for j in range(tdf_2.shape[1])]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf_2.rename(columns={'feature0':'image_name'}, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tdf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#for l in range(len(tdf_2)):\n#    tdf_2[\"image_name\"][l]= str(tdf_2[\"image_name\"][l]).replace(\".jpg\", \"\")\n#tdf_2.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1 = test.merge(tdf_2, on='image_name', how='left')\n#test_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.loc[test_com_1['sex'] == 'female', 'sex'] = 0\n#test_com_1.loc[test_com_1['sex'] == 'male', 'sex'] = 1\n#test_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1['sex'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#null_columns=test_com_1.columns[test_com_1.isnull().any()]\n#test_com_1[null_columns].isnull().sum()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1['anatom_site_general_challenge'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'torso', 'anatom_site_general_challenge'] = 0\n#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'lower extremity', 'anatom_site_general_challenge'] = 1\n#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'upper extremity', 'anatom_site_general_challenge'] = 2\n#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'head/neck', 'anatom_site_general_challenge'] = 3\n#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'palms/soles', 'anatom_site_general_challenge'] = 4\n#test_com_1.loc[test_com_1['anatom_site_general_challenge'] == 'oral/genital', 'anatom_site_general_challenge'] = 5\n#test_com_1['anatom_site_general_challenge'] = test_com_1['anatom_site_general_challenge'].fillna(0)\n#test_com_1['anatom_site_general_challenge'].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.drop(['image_name', 'patient_id'], axis=1, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_com_1.to_csv(\"m_test.csv\", index = False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Use the forest's predict method on the test data\n#tpredictions = rf.predict(test_com_1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#tpredictions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#type(tpredictions)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#yy = list(tpredictions)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#type(yy)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#type(test_lst_1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#sdf = pd.DataFrame(list(zip(test['image_name'], yy)), \n#               columns =['image_name', 'target']) \n#sdf.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test['image_name']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#sdf.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#sdf.to_csv(\"Mahesh_RF_Sub_2.csv\", index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"XGBoost","metadata":{}},{"cell_type":"code","source":"from xgboost.sklearn import XGBClassifier\n#from sklearn import cross_validation, metrics   #Additional scklearn functions\nfrom sklearn.model_selection import GridSearchCV   #Perforing grid search\n\nimport matplotlib.pylab as plt\nfrom matplotlib.pylab import rcParams\nrcParams['figure.figsize'] = 12, 4","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"xgb1 = XGBClassifier(\n learning_rate =0.1,\n n_estimators=1000,\n max_depth=5,\n min_child_weight=1,\n gamma=0,\n subsample=0.8,\n colsample_bytree=0.8,\n objective= 'binary:logistic',\n nthread=4,\n scale_pos_weight=1,\n seed=27)\nxgb1.fit(X_train, y_train)\n# Use the forest's predict method on the test data\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = xgb1.predict(X_val)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Confusion Matrix\nfrom sklearn.metrics import confusion_matrix\ncm = confusion_matrix(y_val, predictions)\nprint (cm)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Accuracy\nfrom sklearn.metrics import accuracy_score\nacc = accuracy_score(y_val, predictions)\nprint (acc)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Recall\nfrom sklearn.metrics import recall_score\nrec = recall_score(y_val, predictions, average=None)\nprint (rec)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Precision\nfrom sklearn.metrics import precision_score\nprec = precision_score(y_val, predictions, average=None)\nprint (prec)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import f1_score\nf1 = f1_score(y_val, predictions, average=None)\nprint (f1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_test1 = {\n 'max_depth':range(3,10,2),\n 'min_child_weight':range(1,6,2)\n}\ngsearch1 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=100, max_depth=5,\n min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8,\n objective= 'binary:logistic', nthread=4, scale_pos_weight=1, seed=27), \n param_grid = param_test1, scoring='roc_auc',n_jobs=4,iid=False, cv=5)\ngsearch1.fit(X_train, y_train)\ngsearch1.grid_scores_, gsearch1.best_params_, gsearch1.best_score_","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}