#amount of trains in each station
from plotly.offline import plot
from plotly.graph_objs import *
x = trips.toPandas()['trip_headsign']
data = Data([Histogram(x=x)])
p = plot(data, filename = 'basic_histogram', output_type = 'div')
displayHTML(p)



# Graph of amount of stops for each train route
from plotly.offline import plot
from plotly.graph_objs import *

# Create random data with numpy
import numpy as np

# Create a trace
trace = go.Scatter(x = lineinfo.toPandas()['vehicle_id'], y = lineinfo.toPandas()['nr_of_stops'],mode = 'markers')

data = [trace]

# Plot and embed in ipython notebook!
p = plot(data, filename = 'basic_histogram', output_type = 'div')
displayHTML(p)

#graph of arrival delays per station (boxplot)
from plotly.offline import plot
import plotly.graph_objs as go
X = trip_updates.toPandas()['arrival_delay'] / 60
data = [go.Box(y = X, x =trip_updates.toPandas()['label'])]
p = plot(data, filename='Boxplots_arrival_delay',output_type='div', validate = False)
displayHTML(p)

# graph of departure delays per station (boxplot)
from plotly.offline import plot
import plotly.graph_objs as go
X = trip_updates.toPandas()['departure_delay'] / 60
data = [go.Box(y = X, x =trip_updates.toPandas()['label'])]
p = plot(data, filename='Boxplots_departure_delay',output_type='div', validate = False)
displayHTML(p)
# graph of arrival delays per train type
from pyspark.sql.functions import udf
from pyspark.sql.types import StringType, FloatType, IntegerType
import re
import time
from plotly.offline import plot
import plotly.graph_objs as go
trainType = udf(lambda x: re.findall("[a-zA-Z]+", x)[0], StringType())
trip_updates = trip_updates.withColumn('train_type', trainType("id"))

X = trip_updates.toPandas()['arrival_delay'] / 60
data = [go.Box(y = X, x =trip_updates.toPandas()['train_type'])]
p = plot(data, filename='Boxplots_arrival_delay',output_type='div', validate = False)
displayHTML(p)
# Boxplot of train delays per train type
X = trip_updates.toPandas()['departure_delay'] / 60
data = [go.Box(y = X, x =trip_updates.toPandas()['train_type'])]
p = plot(data, filename='Boxplots_arrival_delay',output_type='div', validate = False)
displayHTML(p)