#!/usr/bin/env python
# coding: utf-8

# <H1> Toronto Neighborhood Map </H1>

# <h2>Step 1<h>

# <h3> ***Textbook Created*** <h>

# <h2> Step 2 <h>

# In[109]:


import numpy as np 
import pandas as pd 
import requests 
import folium
get_ipython().system('pip install lxml')
get_ipython().system('pip install beautifulsoup4')
get_ipython().system('pip install geocoder')


# In[94]:


df = pd.read_html('https://en.wikipedia.org/wiki/List_of_postal_codes_of_Canada:_M')[0]
df.head(15)


# In[95]:


df.dtypes


# <h2> Step 3 <h>

# In[99]:


#Only process the cells that have an assigned borough. Ignore cells with a borough that is Not assigned. - [X]

df.drop(df[df['Borough']=="Not assigned"].index,axis=0, inplace=True)

#More than one neighborhood can exist in one postal code area. For example, in the table on the Wikipedia page, 
#you will notice that M5A is listed twice and has two neighborhoods: Harbourfront and Regent Park. 
#These two rows will be combined into one row with the neighborhoods separated with a comma as shown in row 11 in 
#the above table.

df['Neighborhood'] = df.groupby("Postal Code")["Neighborhood"].transform(lambda neigh: ', '.join(neigh))

#If a cell has a borough but a Not assigned neighborhood, then the neighborhood will be the same as the borough.

df['Neighborhood'].replace("Not assigned", df["Borough"],inplace=True)


# In[102]:


df.shape


# In[103]:


df.head()


# <h1> Stage 2 <h>

# In[104]:


# Now that you have built a dataframe of the postal code of each neighborhood along with 
# the borough name and neighborhood name, in order to utilize the Foursquare location data, 
# we need to get the latitude and the longitude coordinates of each neighborhood.

df2 = pd.read_csv("https://cocl.us/Geospatial_data")
df2.head()


# In[105]:


df2.dtypes


# In[108]:


df3 = pd.merge(df, df2, on='Postal Code')
df3.head(15)


# <h1> Stage 3 <h>

# In[111]:


import numpy as np 
import pandas as pd 
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)
import json 
get_ipython().system('conda install -c conda-forge geopy --yes')
from geopy.geocoders import Nominatim 
import requests 
from pandas.io.json import json_normalize 
import matplotlib.cm as cm
import matplotlib.colors as colors
from sklearn.cluster import KMeans
get_ipython().system('conda install -c conda-forge folium=0.5.0 --yes')
import folium 
print('Libraries imported.')


# In[121]:


print('The dataframe has {} boroughs and {} postal codes.'.format(
        len(df3['Borough'].unique()),
        df3.shape[0]))


# In[122]:


address = 'Toronto, CA'

geolocator = Nominatim(user_agent="ny_explorer")
location = geolocator.geocode(address)
latitude = location.latitude
longitude = location.longitude
print('The geograpical coordinate of Toronto are {}, {}.'.format(latitude, longitude))


# In[124]:


Toronto_map = folium.Map(location=[latitude, longitude], zoom_start=10)

for lat, lng, borough, neighborhood in zip(df3['Latitude'], df3['Longitude'], df3['Borough'], df3['Neighborhood']):
    label = '{}, {}'.format(neighborhood, borough)
    label = folium.Popup(label, parse_html=True)
    folium.CircleMarker(
        [lat, lng],
        radius=5,
        popup=label,
        color='blue',
        fill=True,
        fill_color='#3186cc',
        fill_opacity=0.7,
        parse_html=False).add_to(Toronto_map)  
    
Toronto_map


# In[ ]: