import pandas as pd
import xgboost as xgb
from sklearn.metrics import confusion_matrix, mean_squared_error
from sklearn.metrics import mean_absolute_error,mean_squared_error,median_absolute_error
df = pd.read_csv('new_work_1.csv',";",header=None)
X_train = df.drop(18,axis=1)
Y_train = df[18]
T_train_xgb = xgb.DMatrix(X_train, Y_train)#
params = {"objective": "reg:linear", "booster":"gblinear"}
gbm = xgb.train(dtrain=T_train_xgb,params=params)
test_data = pd.read_csv('new_work_2.csv',";",header=None)
#print(test_data)
X_test = test_data.drop(18,axis=1)
Y_test = test_data[18]
Y_pred = gbm.predict(xgb.DMatrix(X_test))
test_erorr = mean_squared_error(Y_test,Y_pred);
print("Accuracy: %.2f%%" % (test_erorr * 100.0))	
accuracy = mean_absolute_error(Y_test,Y_pred)
print("Accuracy: %.2f%%" % (accuracy * 100.0))
accuracy2 = median_absolute_error(Y_test, Y_pred)
print("Accuracy: %.2f%%" % (accuracy2 * 100.0))

 from sklearn.metrics import accuracy_score

 import xgboost as xgb
import pandas as pd
import numpy as np
from sklearn.metrics import confusion_matrix, mean_squared_error
from sklearn.datasets import load_iris, load_digits, load_boston
from sklearn.metrics import mean_absolute_error,mean_squared_error,median_absolute_error, accuracy_score
rng = np.random.RandomState(31337)
print("Boston Housing: regression")
df = pd.read_csv('new_work_1.csv',";",header=None)
X_train = df.drop(18,axis=1)
Y_train = df[18]
test_data = pd.read_csv('new_work_2.csv',";",header=None)
#print(test_data)
X_test = test_data.drop(18,axis=1)
Y_test = test_data[18]
xgb_model = xgb.XGBRegressor(max_depth=2, learning_rate=0.6, n_estimators=800)
cl = xgb_model.fit(X_train,Y_train)
predictions = cl.predict(X_test)
actuals = Y_test
print(mean_absolute_error(actuals, predictions))
print(mean_squared_error(actuals, predictions))
print(median_absolute_error(actuals, predictions))
print("============================")

 from sklearn.ensemble import ExtraTreesRegressor
import pandas as pd
import seaborn
import matplotlib.pyplot as plt
from sklearn.metrics import mean_absolute_error,mean_squared_error,median_absolute_error
print("Boston Housing: regression")
df = pd.read_csv('new_work_1.csv',";",header=None)
df_test = df[284000:]
df = df[:284000]
X_train = df.drop(18, axis=1)
Y_train = df[18]
X_test = df_test.drop(18, axis=1)
Y_test = df_test[18]
model = ExtraTreesRegressor()
cl = model.fit(X_train, Y_train)
predictions = pd.Series(cl.predict(X_test))
actuals = Y_test.reset_index(drop=True)
seaborn.set_style()
df_rs = pd.concat([predictions, actuals], axis=1)
df_rs.plot(subplots=True)
print(mean_absolute_error(actuals, predictions))
print(mean_squared_error(actuals, predictions))
print(median_absolute_error(actuals, predictions))
plt.show()