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

# # Built-Up Area Leafiness analysis
# by Robin Wilson (robin@rtwilson.com)

# Import relevant libraries

# In[1]:


import pandas as pd
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')


# Read the CSV data which was exported from the GIS data using QGIS

# In[2]:


df = pd.read_csv('BuiltUpAreas_WithLeaf_WithArea.csv')


# In[3]:


df.columns


# How many rows are there to start with?

# In[4]:


len(df)


# How many rows if we exclude BUA's under 10km^2

# In[5]:


len(df[df.area > 10000000])


# Ok, lets do the rest of our analysis with just these large areas

# In[6]:


large = df[df.area > 10000000]


# What are the top areas if we sort by *mean* leafiness?

# In[7]:


large.sort_values("Leaf_mean", ascending=False).head()


# What are the top areas if we sort by *median* leafiness?

# In[8]:


large.sort_values("Leaf_media", ascending=False).head()


# What are the lowest areas if we sort by mean leafiness

# In[9]:


large.sort_values("Leaf_mean", ascending=True).head()


# What are the areas that have the most variability in their leafiness? Each area has a very different
# mean leafiness value, so we can't just compare standard deviation values. Instead, we'll calculate the co-efficient of variation (standard deviation as a proportion of the mean) and look at the variability in that.

# In[10]:


large['Leaf_cv'] = large.Leaf_stdev / large.Leaf_mean


# In[11]:


large.sort_values("Leaf_cv", ascending=False).head()


# and the least variability?

# In[12]:


large.sort_values('Leaf_cv', ascending=True).head()


# Now let's have a look at this on a graph...

# In[13]:


from bokeh.plotting import figure, ColumnDataSource
from bokeh.models import HoverTool


def scatter_with_hover(df, x, y,
                       fig=None, cols=None, name=None, marker='x',
                       fig_width=500, fig_height=500, **kwargs):
    """
    Plots an interactive scatter plot of `x` vs `y` using bokeh, with automatic
    tooltips showing columns from `df`.

    Parameters
    ----------
    df : pandas.DataFrame
        DataFrame containing the data to be plotted
    x : str
        Name of the column to use for the x-axis values
    y : str
        Name of the column to use for the y-axis values
    fig : bokeh.plotting.Figure, optional
        Figure on which to plot (if not given then a new figure will be created)
    cols : list of str
        Columns to show in the hover tooltip (default is to show all)
    name : str
        Bokeh series name to give to the scattered data
    marker : str
        Name of marker to use for scatter plot
    **kwargs
        Any further arguments to be passed to fig.scatter

    Returns
    -------
    bokeh.plotting.Figure
        Figure (the same as given, or the newly created figure)

    Example
    -------
    fig = scatter_with_hover(df, 'A', 'B')
    show(fig)

    fig = scatter_with_hover(df, 'A', 'B', cols=['C', 'D', 'E'], marker='x', color='red')
    show(fig)

    Author
    ------
    Robin Wilson <robin@rtwilson.com>
    with thanks to Max Albert for original code example
    """

    # If we haven't been given a Figure obj then create it with default
    # size etc.
    if fig is None:
        fig = figure(width=fig_width, height=fig_height, tools=['box_zoom', 'reset'])

    # We're getting data from the given dataframe
    source = ColumnDataSource(data=df)

    # We need a name so that we can restrict hover tools to just this
    # particular 'series' on the plot. You can specify it (in case it
    # needs to be something specific for other reasons), otherwise
    # we just use 'main'
    if name is None:
        name = 'main'

    # Actually do the scatter plot - the easy bit
    # (other keyword arguments will be passed to this function)
    fig.scatter(x, y, source=source, name=name, marker=marker, **kwargs)

    # Now we create the hover tool, and make sure it is only active with
    # the series we plotted in the previous line
    hover = HoverTool(names=[name])

    if cols is None:
        # Display *all* columns in the tooltips
        hover.tooltips = [(c, '@' + c) for c in df.columns]
    else:
        # Display just the given columns in the tooltips
        hover.tooltips = [(c, '@' + c) for c in cols]

    #hover.tooltips.append(('index', '$index'))

    # Finally add/enable the tool
    fig.add_tools(hover)

    return fig


# In[ ]:





# In[14]:


fig = scatter_with_hover(large, 'Leaf_mean', 'Leaf_cv', cols=['name'])
fig.xaxis.axis_label = "Leafiness Mean"
fig.yaxis.axis_label = "Leafiness CV"


# In[15]:


from bokeh.io import output_notebook
from bokeh.plotting import show


# In[16]:


output_notebook()


# In[17]:


show(fig)


# In[ ]: