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

# # Breweries in the United States in 2011

# In[1]:


from IPython.display import HTML

HTML('''<script>
code_show=true; 
function code_toggle() {
 if (code_show){
 $('div.input').hide();
 } else {
 $('div.input').show();
 }
 code_show = !code_show
} 
$( document ).ready(code_toggle);
</script>
<form action="javascript:code_toggle()"><input type="submit" value="Click here to toggle on/off the raw code."></form>''')


# The following shows number of breweries in the United States in 2011 per state, along breweries per capita per state and breweries per sq mi per state. Population data was taken from 2010 census.

# In[2]:


import pandas as pd
population = pd.read_csv('./../data/pop_density.csv', skiprows=3, index_col=0)['2010_POPULATION'].to_dict()


# In[3]:


area_string = '''Alaska	1	663,267 sq mi	1,717,854 sq km
Texas	2	268,580 sq mi	695,621 sq km
California	3	163,695 sq mi	423,970 sq km
Montana	4	147,042 sq mi	380,838 sq km
New Mexico	5	121,589 sq mi	314,915 sq km
Arizona	6	113,998 sq mi	295,254 sq km
Nevada	7	110,560 sq mi	286,351 sq km
Colorado	8	104,093 sq mi	269,601 sq km
Oregon	9	98,380 sq mi	254,805 sq km
Wyoming	10	97,813 sq mi	253,336 sq km
Michigan	11	96,716 sq mi	250,494 sq km
Minnesota	12	86,938 sq mi	225,171 sq km
Utah	13	84,898 sq mi	219,887 sq km
Idaho	14	83,570 sq mi	216,446 sq km
Kansas	15	82,276 sq mi	213,096 sq km
Nebraska	16	77,358 sq mi	200,356 sq km
South Dakota	17	77,121 sq mi	199,742 sq km
Washington	18	71,300 sq mi	184,665 sq km
North Dakota	19	70,700 sq mi	183,112 sq km
Oklahoma	20	69,899 sq mi	181,035 sq km
Missouri	21	69,704 sq mi	180,533 sq km
Florida	22	65,755 sq mi	170,304 sq km
Wisconsin	23	65,498 sq mi	169,639 sq km
Georgia	24	59,425 sq mi	153,909 sq km
Illinois	25	57,914 sq mi	149,998 sq km
Iowa	26	56,271 sq mi	145,743 sq km
New York	27	54,556 sq mi	141,299 sq km
North Carolina	28	53,818 sq mi	139,389 sq km
Arkansas	29	53,179 sq mi	137,732 sq km
Alabama	30	52,419 sq mi	135,765 sq km
Louisiana	31	51,840 sq mi	134,264 sq km
Mississippi	32	48,431 sq mi	125,434 sq km
Pennsylvania	33	46,056 sq mi	119,283 sq km
Ohio	34	44,825 sq mi	116,096 sq km
Virginia	35	42,774 sq mi	110,785 sq km
Tennessee	36	42,144 sq mi	109,151 sq km
Kentucky	37	40,410 sq mi	104,659 sq km
Indiana	38	36,418 sq mi	94,321 sq km
Maine	39	35,385 sq mi	91,646 sq km
South Carolina	40	32,020 sq mi	82,932 sq km
West Virginia	41	24,230 sq mi	62,755 sq km
Maryland	42	12,407 sq mi	32,133 sq km
Hawaii	43	10,931 sq mi	28,311 sq km
Massachusetts	44	10,555 sq mi	27,336 sq km
Vermont	45	9,615 sq mi	24,901 sq km
New Hampshire	46	9,350 sq mi	24,216 sq km
New Jersey	47	8,722 sq mi	22,588 sq km
Connecticut	48	5,544 sq mi	14,357 sq km
Delaware	49	2,489 sq mi	6,447 sq km
Rhode Island	50	1,545 sq mi	4,002 sq km
District of Columbia	51	68.25 sq mi	176.75 sq km'''

area_string = area_string.replace('sq mi', '').replace('sq km', '')

area = dict()

for l in area_string.splitlines():
    data = l.split()
    size = int(float(data[-2].replace(',', '')))
    name = ' '.join(data[0:-3])
    area[name] = size


# In[4]:


df = pd.read_csv('./../data/breweries.csv', index_col=0)

df.columns

us_df = df[df['country']=='United States'].copy(deep=True)

us_df.loc[471, 'state'] = 'Florida'

us_df = us_df[~ us_df['state'].isnull()]

us_df.loc[1393, 'state'] = 'Maine'
us_df.loc[1397, 'state'] = 'Kansas'
us_df.loc[1398, 'state'] = 'Illinois'
us_df.loc[1399, 'state'] = 'New Jersey'
us_df.loc[1402, 'state'] = 'New York'
us_df.loc[1404, 'state'] = 'Missouri'
us_df.loc[[1407, 1413], 'state'] = 'North Carolina'
us_df.loc[[1409], 'state'] = 'Ohio'
us_df.loc[[1410], 'state'] = 'Wisconsin'
us_df.loc[[1411], 'state'] = 'Massachusetts'
us_df.loc[[1416], 'state'] = 'Michigan'
us_df.loc[[1417, 1418], 'state'] = 'Oregon'
us_df.loc[[1420], 'state'] = 'California'
us_df.loc[[1421], 'state'] = 'District of Columbia'

us_df = us_df[us_df['state'] != 'Virgin Islands']
us_df = us_df[us_df['state'] != 'District of Columbia']


states = dict()
for s in sorted(us_df['state'].unique()):
    states[s] = dict()
    states[s]['area'] = area[s]
    states[s]['population'] = population[s]
    states[s]['count'] = len(us_df[us_df['state'] == s])


states_df = pd.DataFrame(states).T

states_df['per_capita'] = states_df['count']/states_df['population']
states_df['per_sqmiles'] = states_df['count']/states_df['area']
states_df['states'] = states_df.index
states_df = states_df.sort_values('count', ascending=False)


# In[5]:


states_df.head()


# In[6]:


northeast = ['New Jersey', 'New York', 'Pennsylvania', 'Connecticut', 'Maine', 'Massachusetts', 'New Hampshire', 'Rhode Island', 'Vermont']
midwest = ['Illinois', 'Indiana', 'Michigan', 'Ohio', 'Wisconsin', 'Iowa', 'Kansas', 'Minnesota', 'Missouri', 'Nebraska', 'North Dakota', 'South Dakota']
south = ['Delaware', 'Florida', 'Georgia', 'Maryland', 'North Carolina', 'South Carolina', 'Virginia', 'District of Columbia', 'West Virginia', 'Alabama', 'Kentucky', 'Mississippi', 'Tennessee', 
        'Arkansas', 'Louisiana', 'Oklahoma', 'Texas']
west = ['Arizona', 'Colorado', 'Idaho', 'Montana', 'Nevada', 'New Mexico', 'Utah', 'Wyoming',
       'Alaska', 'California', 'Hawaii', 'Oregon', 'Washington']


# In[7]:


def f(v):
    if v in northeast:
        return 'northeast'
    elif v in midwest:
        return 'midwest'
    elif v in south:
        return 'south'
    elif v in west:
        return 'west'
    else:
        return 'other'

states_df['region'] = states_df['states'].apply(f)


# In[8]:


states_df['population_format'] = states_df['population'].apply(lambda x: "{:,}".format(x))
states_df['area_format'] = states_df['area'].apply(lambda x: "{:,}".format(x))

states_df['x'] = range(0, len(states_df.index))
states_df['states'] = states_df.index
states_df['count_by_2'] = states_df['count']/2
states_df['color'] = '#1F77B4'


# In[9]:


import bokeh
from bokeh.models import ( ColumnDataSource, HoverTool, Circle, CategoricalColorMapper,
                          LinearInterpolator, Row, 
                          CategoricalTickFormatter, CustomJS,
                          Rect,  )
from bokeh.plotting import figure
from bokeh.io import output_notebook, show
output_notebook()


# ### Number of breweries and per capita vs per sq. mile breweries

# In[10]:


source = ColumnDataSource(data=states_df)
size_mapper = LinearInterpolator(x=[states_df['population'].min(), states_df['population'].max()], y=[2, 10])

hover1 = HoverTool(
        tooltips="""
        <div>
            <div>
                <span style="font-size: 15px; color: #966;">[@index]</span>
            </div>
            <div>
                <span style="font-size: 17px;">Population: </span><span style="font-size: 17px; font-weight: bold;">@population_format</span>
            </div>
            <div>
                <span style="font-size: 17px;">Area(sq mi): </span><span style="font-size: 17px; font-weight: bold;">@area_format</span>
            </div>
        </div>
        """,
    )


p1 = figure(width=475, height=400, tools='pan,box_select,box_zoom,reset')
p1.x_range.bounds = (0, 3e-5)
p1.x_range.end = 3e-5
p1.y_range.bounds = (0, 3e-3)
p1.y_range.end = 3e-3
circle = Circle(x='per_capita', y='per_sqmiles',
         radius_units='screen', fill_color='color',
         radius={'field':'population', 'transform': size_mapper},)
p1.add_glyph(source, circle)
p1.xaxis.axis_label = 'Breweries Per Capita'
p1.yaxis.axis_label = 'Breweries Per Sq Mile'

hover2 = HoverTool(
        tooltips="""
        <div>
            <div>
                <span style="font-size: 15px; color: #966;">[@states]</span>
            </div>
            <div>
                <span style="font-size: 17px;">Count: </span><span style="font-size: 17px; font-weight: bold;">@count</span>
            </div>
        </div>
        """,
    )

p2 = figure(width=475, height=400, x_range=list(states_df.index), tools='pan,box_select,box_zoom,reset')
rect = Rect(x='states', y='count_by_2', width=1, height='count', fill_color='color')
p2.y_range.bounds = (0, 150)
p2.y_range.start = 0
p2.xaxis.major_label_orientation = 3.14 / 3
p2.x_range.bounds = list(states_df.index)
p2.add_glyph(source, rect)
p2.yaxis.axis_label = 'Number of breweries'


callback1 = CustomJS(args=dict(source=source, hover=hover2), code="""

for (i=0; i < source.data.color.length; i++) {
    source.data.color[i] = '#1F77B4'
}

var indices = cb_data.index['1d'].indices;
for (i=0; i < indices.length; i++) {
    ind0 = indices[i]
    source.data.color[ind0] = '#b4531f'   
}

source.trigger('change')

""")


callback2 = CustomJS(args=dict(source=source, hover=hover1), code="""

for (i=0; i < source.data.color.length; i++) {
    source.data.color[i] = '#1F77B4'
}

var indices = cb_data.index['1d'].indices;
for (i=0; i < indices.length; i++) {
    ind0 = indices[i]
    source.data.color[ind0] = '#b4531f'   

}

source.trigger('change')

""")


hover1.callback = callback1
hover2.callback = callback2


p1.add_tools(hover1)
p2.add_tools(hover2)


p = Row(p2, p1)

show(p)


# #### Breweries by region

# In[11]:


import geopandas as gpd
import numpy as np

def getXYCoords(geometry, coord_type):
    """ Returns either x or y coordinates from  geometry coordinate sequence. Used with LineString and Polygon geometries."""
    if coord_type == 'x':
        return geometry.coords.xy[0]
    elif coord_type == 'y':
        return geometry.coords.xy[1]

def getPolyCoords(geometry, coord_type):
    """ Returns Coordinates of Polygon using the Exterior of the Polygon."""
    ext = geometry.exterior
    return getXYCoords(ext, coord_type)
    
def getLineCoords(geometry, coord_type):
    """ Returns Coordinates of Linestring object."""
    return getXYCoords(geometry, coord_type)

def getPointCoords(geometry, coord_type):
    """ Returns Coordinates of Point object."""
    if coord_type == 'x':
        return geometry.x
    elif coord_type == 'y':
        return geometry.y
    
def multiGeomHandler(multi_geometry, coord_type, geom_type):
    """ 
    Function for handling multi-geometries. Can be MultiPoint, MultiLineString or MultiPolygon. 
    Returns a list of coordinates where all parts of Multi-geometries are merged into a single list. 
    Individual geometries are separated with np.nan which is how Bokeh wants them. 
    # Bokeh documentation regarding the Multi-geometry issues can be found here (it is an open issue)
    # https://github.com/bokeh/bokeh/issues/2321
    """
    
    for i, part in enumerate(multi_geometry):
        # On the first part of the Multi-geometry initialize the coord_array (np.array)
        if i == 0:
            if geom_type == "MultiPoint":
                coord_arrays = np.append(getPointCoords(part, coord_type), np.nan)
            elif geom_type == "MultiLineString":
                coord_arrays = np.append(getLineCoords(part, coord_type), np.nan)
            elif geom_type == "MultiPolygon":
                coord_arrays = np.append(getPolyCoords(part, coord_type), np.nan)
        else:
            if geom_type == "MultiPoint":
                coord_arrays = np.concatenate([coord_arrays, np.append(getPointCoords(part, coord_type), np.nan)])
            elif geom_type == "MultiLineString":
                coord_arrays = np.concatenate([coord_arrays, np.append(getLineCoords(part, coord_type), np.nan)])
            elif geom_type == "MultiPolygon":
                coord_arrays = np.concatenate([coord_arrays, np.append(getPolyCoords(part, coord_type), np.nan)])
    
    # Return the coordinates 
    return coord_arrays
    

def getCoords(row, geom_col, coord_type):
    """
    Returns coordinates ('x' or 'y') of a geometry (Point, LineString or Polygon) as a list (if geometry is LineString or Polygon). 
    Can handle also MultiGeometries.
    """
    # Get geometry
    geom = row[geom_col]
    
    # Check the geometry type
    gtype = geom.geom_type
    
    # "Normal" geometries
    # -------------------
    
    if gtype == "Point":
        return getPointCoords(geom, coord_type)
    elif gtype == "LineString":
        return list( getLineCoords(geom, coord_type) )
    elif gtype == "Polygon":
        return list( getPolyCoords(geom, coord_type) )
        
    # Multi geometries
    # ----------------
    
    else:
        return list( multiGeomHandler(geom, coord_type, gtype) ) 
    
data = gpd.read_file('../data/states_21basic/states.shp')

data = data.to_crs(crs=data.crs)

data['geom_x'] = data.apply(getCoords, geom_col="geometry", coord_type="x", axis=1)
data['geom_y'] = data.apply(getCoords, geom_col="geometry", coord_type="y", axis=1)

data = data.drop('geometry', axis=1)
plot_df = pd.merge(data, states_df, left_on='STATE_NAME', right_index=True)
dfsource = ColumnDataSource(data=plot_df)


# In[12]:


WIDTH = 900
TOOLS = "pan,wheel_zoom,box_zoom,reset,save"
p = figure(width=int(WIDTH), height=int(WIDTH/1.5),
    title="", tools=TOOLS,
    x_axis_location=None, y_axis_location=None
)

palette = ['#a6cee3',
'#1f78b4',
'#b2df8a',
'#33a02c']

color_mapper = CategoricalColorMapper(factors=list(states_df['region'].unique()), palette=palette)
# alpha_mapper = LinearInterpolator(x=[states_df['count'].min(), states_df['count'].max()], y=[.1, 1])

patches = p.patches('geom_x', 'geom_y', 
          source=dfsource, name='Name',
          fill_color={'field': 'region', 'transform': color_mapper}, line_color="white", line_width=0.5)

hover = HoverTool(renderers=[patches])
hover.tooltips=[("Name", "@states"),("Count", "@count")]

p.add_tools(hover)

show(p)


# In[13]:


source = ColumnDataSource(data=states_df)

hover1 = HoverTool(
        tooltips="""
        <div>
            <div>
                <span style="font-size: 15px; color: #966;">[@index]</span>
            </div>
            <div>
                <span style="font-size: 17px;">Population: </span><span style="font-size: 17px; font-weight: bold;">@population_format</span>
            </div>
            <div>
                <span style="font-size: 17px;">Area(sq mi): </span><span style="font-size: 17px; font-weight: bold;">@area_format</span>
            </div>
        </div>
        """,
    )


p1 = figure(width=475, height=400, tools='pan,box_select,box_zoom,reset')
p1.x_range.bounds = (0, 3e-5)
p1.x_range.end = 3e-5
p1.y_range.bounds = (0, 3e-3)
p1.y_range.end = 3e-3
circle = Circle(x='per_capita', y='per_sqmiles',
         radius_units='screen', fill_color={'field': 'region', 'transform': color_mapper},
         radius={'field':'population', 'transform': size_mapper},)
p1.add_glyph(source, circle)
p1.xaxis.axis_label = 'Breweries Per Capita'
p1.yaxis.axis_label = 'Breweries Per Sq Mile'

hover2 = HoverTool(
        tooltips="""
        <div>
            <div>
                <span style="font-size: 15px; color: #966;">[@states]</span>
            </div>
            <div>
                <span style="font-size: 17px;">Count: </span><span style="font-size: 17px; font-weight: bold;">@count</span>
            </div>
        </div>
        """,
    )

p2 = figure(width=475, height=400, x_range=list(states_df.index), tools='pan,box_select,box_zoom,reset')
rect = Rect(x='states', y='count_by_2', width=1, height='count', fill_color={'field': 'region', 'transform': color_mapper},)
p2.y_range.bounds = (0, 150)
p2.y_range.start = 0
p2.xaxis.major_label_orientation = 3.14 / 3
p2.x_range.bounds = list(states_df.index)
p2.add_glyph(source, rect)
p2.yaxis.axis_label = 'Number of breweries'

p1.add_tools(hover1)
p2.add_tools(hover2)


p = Row(p2, p1)

show(p)


# ##### States with the most breweries

# In[14]:


pd.DataFrame(states_df.sort_values('count', ascending=False).head(5)['count'])


# ###### States with highest breweries per capita

# In[15]:


pd.DataFrame(states_df.sort_values('per_capita', ascending=False).head(5)['per_capita'])


# ###### States with highest breweries per sq. mile

# In[16]:


pd.DataFrame(states_df.sort_values('per_sqmiles', ascending=False).head(5)['per_sqmiles'])


# In[ ]: