Fixes : #6551

machine_learning/xgboostclassifier.py

@@ -0,0 +1,55 @@
+from xgboost import XGBClassifier
+#https://xgboost.readthedocs.io/en/stable/
+import numpy as np 
+import pandas as pd 
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+
+
+training = pd.read_csv('../input/titanic/train.csv')
+test = pd.read_csv('../input/titanic/test.csv')
+
+# Commented out IPython magic to ensure Python compatibility.
+training['train_test'] = 1
+test['train_test'] = 0
+test['Survived'] = np.NaN
+all_data = pd.concat([training,test])
+# %matplotlib inline
+all_data.columns
+
+all_data.describe()
+
+all_data['cabin_mul']=all_data.Cabin.apply(lambda x: 0 if pd.isna(x) else len(x.split(' ')))
+all_data['cabin_adv'] = all_data.Cabin.apply(lambda x: str(x)[0])
+all_data['name_title']= all_data.Name.apply(lambda x: x.split(',')[1].split('.')[0].strip())
+all_data.Age=all_data.Age.fillna(training.Age.median())
+all_data.Fare=all_data.Fare.fillna(training.Fare.median())
+all_data.dropna(subset=['Embarked'],inplace=True)
+all_data['norm_fare']=np.log(all_data.Fare+1)
+all_data.Pclass=all_data.Pclass.astype(str)
+all_data['Age']=all_data['Age'].apply(np.int64)
+all_dummies = pd.get_dummies(all_data[['Pclass','Sex','Age','SibSp','Parch','norm_fare',
+                                       'Embarked','cabin_adv','cabin_mul',
+                                       'name_title','train_test']])
+
+from sklearn.preprocessing import StandardScaler
+scale = StandardScaler()
+all_dummies_scaled = all_dummies.copy()
+all_dummies_scaled[['Age','SibSp','Parch','norm_fare']]= scale.fit_transform(all_dummies_scaled[['Age','SibSp','Parch','norm_fare']])
+all_dummies_scaled.head()
+
+X_train_scaled = all_dummies_scaled[all_dummies_scaled.train_test == 1].drop(['train_test'], axis =1)
+X_test_scaled = all_dummies_scaled[all_dummies_scaled.train_test == 0].drop(['train_test'], axis =1)
+
+y_train = all_data[all_data.train_test==1].Survived
+
+from xgboost import XGBClassifier
+
+xgb = XGBClassifier()
+xgb.fit(X_train_scaled,y_train)
+
+y_hat_base_vc = xgb.predict(X_test_scaled).astype(int)
+basic_submission = {'PassengerId': test.PassengerId, 'Survived': y_hat_base_vc}
+base_submission = pd.DataFrame(data=basic_submission)
+base_submission.to_csv('xgb_submission.csv', index=False)

machine_learning/xgboostregressor.py

@@ -0,0 +1,138 @@
+from xgboost import XGBRegressor
+#https://xgboost.readthedocs.io/en/stable/
+import numpy as np 
+import pandas as pd
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+
+import os
+for dirname, _, filenames in os.walk('/kaggle/input'):
+    for filename in filenames:
+        print(os.path.join(dirname, filename))
+
+trainAmes=pd.read_csv('/kaggle/input/ames-housing-dataset/AmesHousing.csv')
+test=pd.read_csv('/kaggle/input/house-prices-advanced-regression-techniques/test.csv')
+train=pd.read_csv('/kaggle/input/house-prices-advanced-regression-techniques/train.csv')
+
+trainAmes.columns = trainAmes.columns.str.replace(' ', '')
+trainAmes=trainAmes.rename(columns={"YearRemod/Add": "YearRemodAdd"})
+
+data=pd.concat([trainAmes,train,test], axis=0, sort=False)
+print("Size of the Housing Dataset",len(data))
+useless = ['Id','PID','Order','SalePrice'] 
+data = data.drop(useless, axis = 1)
+duplicate = data[data.duplicated(keep='last')].index
+len(duplicate)
+
+duplicate=duplicate[0:390]
+trainAmes = trainAmes.drop(duplicate, axis = 0)
+
+training=pd.concat([trainAmes,train], axis=0, sort=False)
+useless = ['Id','PID','Order'] 
+training = training.drop(useless, axis = 1)
+
+# Separating Target and Features
+
+target = training['SalePrice']
+test_id = test['Id']
+test = test.drop(['Id'],axis = 1)
+training2 = training.drop(['SalePrice'], axis = 1)
+
+
+# Concatenating train & test set
+
+train_test = pd.concat([training2,test], axis=0, sort=False)
+
+# Filling Categorical NaN (That we know how to fill due to the description file )
+
+train_test['Functional'] = train_test['Functional'].fillna('Typ')
+train_test['Electrical'] = train_test['Electrical'].fillna("SBrkr")
+train_test['KitchenQual'] = train_test['KitchenQual'].fillna("TA")
+train_test['Exterior1st'] = train_test['Exterior1st'].fillna(train_test['Exterior1st'].mode()[0])
+train_test['Exterior2nd'] = train_test['Exterior2nd'].fillna(train_test['Exterior2nd'].mode()[0])
+train_test['SaleType'] = train_test['SaleType'].fillna(train_test['SaleType'].mode()[0])
+train_test["PoolQC"] = train_test["PoolQC"].fillna("None")
+train_test["Alley"] = train_test["Alley"].fillna("None")
+train_test['FireplaceQu'] = train_test['FireplaceQu'].fillna("None")
+train_test['Fence'] = train_test['Fence'].fillna("None")
+train_test['MiscFeature'] = train_test['MiscFeature'].fillna("None")
+for col in ('GarageArea', 'GarageCars'):
+    train_test[col] = train_test[col].fillna(0)
+
+for col in ['GarageType', 'GarageFinish', 'GarageQual', 'GarageCond']:
+    train_test[col] = train_test[col].fillna('None')
+
+for col in ('BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2'):
+    train_test[col] = train_test[col].fillna('None')
+
+for col in ('BsmtFinSF1', 'BsmtFinSF2', 'BsmtFullBath', 'BsmtHalfBath', 'MasVnrArea','BsmtUnfSF', 'TotalBsmtSF'):
+    train_test[col] = train_test[col].fillna(0)
+
+train_test['LotFrontage'] = train_test['LotFrontage'].fillna(train['LotFrontage'].median())
+
+    # Checking the features with NaN remained out
+
+for col in train_test:
+    if train_test[col].isna().sum() > 0:
+        print(train_test[col][1])
+
+# Converting non-numeric predictors stored as numbers into string
+
+train_test['MSSubClass'] = train_test['MSSubClass'].apply(str)
+train_test['YrSold'] = train_test['YrSold'].apply(str)
+train_test['MoSold'] = train_test['MoSold'].apply(str)
+train_test['OverallQual'] = train_test['OverallQual'].apply(str)
+train_test['OverallCond'] = train_test['OverallCond'].apply(str)
+train_test["SqFtPerRoom"] = train_test["GrLivArea"] / (train_test["TotRmsAbvGrd"] +
+                                                       train_test["FullBath"] +
+                                                       train_test["HalfBath"] +
+                                                       train_test["KitchenAbvGr"])
+
+train_test['Total_Home_Quality'] = train_test['OverallQual'] + train_test['OverallCond']
+
+train_test['Total_Bathrooms'] = (train_test['FullBath'] + (0.5 * train_test['HalfBath']) +
+                               train_test['BsmtFullBath'] + (0.5 * train_test['BsmtHalfBath']))
+
+train_test["HighQualSF"] = train_test["1stFlrSF"] + train_test["2ndFlrSF"]
+train_test['renovated']=train_test['YearRemodAdd']+train_test['YearBuilt']
+
+# Removing the useless variables
+
+useless = ['GarageYrBlt','YearRemodAdd'] 
+train_test = train_test.drop(useless, axis = 1)
+# Creating dummy variables from categorical features
+
+from scipy.stats import skew
+
+train_test_dummy = pd.get_dummies(train_test)
+
+numeric_features = train_test_dummy.dtypes[train_test_dummy.dtypes != object].index
+skewed_features = train_test_dummy[numeric_features].apply(lambda x: skew(x)).sort_values(ascending=False)
+high_skew = skewed_features[skewed_features > 0.5]
+skew_index = high_skew.index
+
+# Normalize skewed features using log_transformation
+
+for i in skew_index:
+    train_test_dummy[i] = np.log1p(train_test_dummy[i] )
+
+target_log = np.log1p(target)
+
+from xgboost import XGBRegressor
+
+# Train-Test separation
+
+X_train = train_test_dummy[0:4000]
+X_test = train_test_dummy[4000:]
+
+xgb = XGBRegressor()
+xgb.fit(X_train,target_log)
+
+test_pred = xgb.predict(X_test)
+submission = pd.DataFrame(test_id, columns = ['Id'])
+test_pred = np.expm1(test_pred)
+submission['SalePrice'] = test_pred 
+submission.head()
+submission.to_csv("xgb.csv", index = False, header = True)