# Necessary imports
import os
import time
import timeit
import numpy as np
import pandas as pd
import scipy
import sklearn
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.utils import resample
import warnings
warnings.filterwarnings('ignore')
%matplotlib inline

# Modelling packages
from sklearn import ensemble
from sklearn.feature_selection import chi2, f_classif, SelectKBest 
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import adjusted_rand_score, classification_report, confusion_matrix, silhouette_score
from sklearn.model_selection import cross_val_score, GridSearchCV, train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import normalize

# Plotly packages
import cufflinks as cf
import ipywidgets as widgets
import plotly as py
import plotly.figure_factory as ff
import plotly.graph_objs as go
from plotly import tools
from scipy import special
py.offline.init_notebook_mode(connected=True)

# Preview the data for listings
listings.head()

# Print the size of the dataframe
print('Size of the dataframe: {} listings x {} features'.format(listings.shape[0],listings.shape[1]))

# Check for any missing values
print('Missing values: \n', listings.isna().sum())

# View descriptive statistics
listings.describe()

# View room types on Airbnb

# Set the size of the chart
plt.rcParams['figure.figsize'] = [5,5]

# Import the data for the pie chart
trace = go.Pie(labels=listings['room_type'].value_counts().index, values = listings['room_type'].value_counts())

# Create the layout
layout = go.Layout(
    title = 'Room Types on Airbnb',
    height = 600,
    width = 800,
    autosize = False
)

# Construct the chart
fig = go.Figure(data = [trace], layout = layout)
py.offline.iplot(fig, filename ='cufflinks/simple')

# Plot the minimum number of nights required for units
plt.rcParams['figure.figsize'] = [10,5]

listings['minimum_nights_temp'] = np.where(listings['minimum_nights'] > 7, 8, listings['minimum_nights'])

plt.title('Minimum number of Nights')
plt.xlabel('Minimum number of nights')
sns.barplot(x = listings['minimum_nights_temp'].value_counts().index,
            y = listings['minimum_nights_temp'].value_counts())

listings.drop('minimum_nights_temp', axis=1)
print()

# View all prices
plt.title('Airbnb Rental Prices (USD/day)')
sns.distplot(listings['price'])

# Examine by removing outliers
plt.xlim(0,370)
plt.title('Airbnb Rental Prices (USD/day)')
sns.distplot(listings['price'], bins=500)

# View most expensive listings in Seattle
listings.sort_values(by = 'price', ascending=False).head(10)

# View # of listings by neighbourhood
plt.rcParams['figure.figsize'] = [10,20]

plt.title('# of Listings')
plt.xticks(rotation=60)
sns.barplot(x = listings['neighbourhood'].value_counts(),
            y = listings['neighbourhood'].value_counts().index)

# Create new dataframe for the statistics on each neighbourhood
neighbourhood_averages = listings.groupby(['neighbourhood']).mean()
neighbourhood_averages

# View # of listings by neighbourhood
plt.rcParams['figure.figsize'] = [10,20]

neighbourhood_averages.sort_values('price', ascending=False, inplace=True)
plt.title('Average price')
plt.xticks(rotation=60)
sns.barplot(x = neighbourhood_averages['price'],
            y = neighbourhood_averages.index)

# Mapbox API credentials
mapbox_access_token = 'pk.eyJ1IjoibWh1aDIyIiwiYSI6IkpGdEhkXzgifQ.Af4NVoaKw7lvlqVyak8Ydw'

# Import the data for the map
data = go.Data([

    go.Scattermapbox(
        lat = neighbourhood_averages['latitude'],
        lon = neighbourhood_averages['longitude'],
        mode='markers',
        marker=go.scattermapbox.Marker(
            size=9
        ),
        text = neighbourhood_averages.price,
    )
])

# Format the layout of the map
layout = go.Layout(
    title = 'Airbnb Units in Seattle',
    height=600,
    autosize=True,
    hovermode='closest',
    mapbox=dict(
        layers=[
            dict(
                sourcetype = 'geojson',
                source = 'neighbourhoods.geojson',
                type = 'fill',
                color = 'rgba(40,0,113,0.8)'
            )
        ],
        accesstoken=mapbox_access_token,
        bearing=0,
        center=dict(
            lat=47.6062,
            lon=-122.3321
        ),
        pitch=0,
        zoom=9.5,
        style='light',
    ),
)

fig = dict(data=data, layout=layout)
py.offline.iplot(fig, filename='county-level-choropleths-python')

get_ipython().run_cell_magic('html', '', '<script src="https://cdn.rawgit.com/parente/4c3e6936d0d7a46fd071/raw/65b816fb9bdd3c28b4ddf3af602bfd6015486383/code_toggle.js"></script>')