import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import datetime
import seaborn as sns
#PLOTLY
import plotly
import plotly.plotly as py
import plotly.offline as offline
import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode,plot,iplot
import cufflinks as cf
cf.set_config_file(offline=True)
from plotly.graph_objs import Scatter, Figure, Layout

data = pd.read_csv('/Users/rustamislamnurov/Desktop/train.csv', nrows=1101)
print(data.head())
print(data.isnull().sum())
#data = data.dropna()
#sns.distplot(data['fare'])
#plt.title('asdda')
from  sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.linear_model import LinearRegression
import xgboost as xgb
from sklearn.ensemble import RandomForestRegressor
ml = data[1000:]
y = ml['fare']
X = ml.drop(['fare','date','time'],axis = 1)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43, test_size = 0.3)
randomForest = RandomForestRegressor(random_state=42)
randomForest.fit(X_train, y_train)
randomForestPredict = randomForest.predict(X_test)
randomForest_mse = mean_squared_error(y_test, randomForestPredict)
randomForestMSE = np.sqrt(randomForest_mse)
print(randomForestMSE)
model = RandomForestRegressor(n_estimators=25, max_features=5, max_depth=25, min_samples_split=3,
                              min_samples_leaf=2, random_state=0)