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

# Cufflinks binds [Plotly](https://plotly.com/python) directly to [pandas](http://pandas.pydata.org/) dataframes.

# In[1]:


import plotly.tools as tls
tls.embed('https://plotly.com/~cufflinks/8')


# #### Packages
# Run `! pip install cufflinks --upgrade` to install Cufflinks. In addition to [Plotly](https://plotly.com/python), [pandas](http://pandas.pydata.org/) and Cufflinks, this tutorial will also use [NumPy](http://www.numpy.org/). 

# In[2]:


import plotly.plotly as py
import cufflinks as cf
import pandas as pd
import numpy as np
print cf.__version__


# #### Dataframes
# With Plotly's Python library, you can describe figures with DataFrame's series and index's

# In[3]:


df = cf.datagen.lines()

py.iplot([{
    'x': df.index,
    'y': df[col],
    'name': col
}  for col in df.columns], filename='cufflinks/simple-line')


# But with `cufflinks`, you can plot them directly

# In[5]:


df.iplot(kind='scatter', filename='cufflinks/cf-simple-line')


# Almost every chart that you make in `cufflinks` will be created with just one line of code.

# In[6]:


df = pd.DataFrame(np.random.randn(1000, 4), columns=['a', 'b', 'c', 'd'])
df.scatter_matrix(filename='cufflinks/scatter-matrix', world_readable=True)


# Charts created with `cufflinks` are synced with your online Plotly account. You'll need to [configure your credentials](https://plotly.com/python/getting-started/) to get started. `cufflinks` can also be configured to work offline in IPython notebooks with [Plotly Offline](https://plotly.com/python/offline). To get started with Plotly Offline, [download a trial library](http://purchasing.plot.ly/plotly-offline-ipython) and run `cf.go_offline()`.

# In[14]:


cf.go_online() # switch back to online mode, where graphs are saved on your online plotly account


# By default, plotly graphs are *public*. Make them private by setting `world_readable` to `False`

# In[15]:


df.a.iplot(kind='histogram', world_readable=False)


# Only *you* (the creator) will be able to see this chart, or change the global, default settings with `cf.set_config_file`

# In[16]:


cf.set_config_file(offline=False, world_readable=True, theme='ggplot')


# ### Chart Types
# ##### Line Charts

# In[17]:


df = pd.DataFrame(np.random.randn(1000, 2), columns=['A', 'B']).cumsum()
df.iplot(filename='cufflinks/line-example')


# Plot one column vs another with `x` and `y` keywords

# In[18]:


df.iplot(x='A', y='B', filename='cufflinks/x-vs-y-line-example')


# ##### Bar Charts
# Download some civic data. A time series log of the 311 complaints in NYC.

# In[ ]:


df = pd.read_csv('https://raw.githubusercontent.com/plotly/widgets/master/ipython-examples/311_150k.csv', parse_dates=True, index_col=1)
df.head(3)


# In[ ]:


series = df['Complaint Type'].value_counts()[:20]
series.head(3)


# Plot a `series` directly

# In[18]:


series.iplot(kind='bar', yTitle='Number of Complaints', title='NYC 311 Complaints',
             filename='cufflinks/categorical-bar-chart')


# Plot a dataframe row as a bar

# In[19]:


df = pd.DataFrame(np.random.rand(10, 4), columns=['A', 'B', 'C', 'D'])
row = df.ix[5]
row.iplot(kind='bar', filename='cufflinks/bar-chart-row')


# Call `iplot(kind='bar')` on a dataframe to produce a grouped bar chart

# In[20]:


df.iplot(kind='bar', filename='cufflinks/grouped-bar-chart')


# In[21]:


df.iplot(kind='bar', barmode='stack', filename='cufflinks/grouped-bar-chart')


# Remember: plotly charts are interactive. Click on the legend entries to hide-and-show traces, click-and-drag to zoom, double-click to autoscale, shift-click to drag.
# 
# ![Click on legend entries to hide and show traces](http://i.imgur.com/419Bmdy.gif)

# Make your bar charts horizontal with `kind='barh'`

# In[22]:


df.iplot(kind='barh',barmode='stack', bargap=.1, filename='cufflinks/barh')


# ##### Themes
# 
# cufflinks ships with a few themes. View available themes with `cf.getThemes`, apply them with `cf.set_config_file`

# In[23]:


cf.getThemes()


# In[24]:


cf.set_config_file(theme='pearl')


# ##### Histograms

# In[4]:


df = pd.DataFrame({'a': np.random.randn(1000) + 1,
                   'b': np.random.randn(1000),
                   'c': np.random.randn(1000) - 1})

df.iplot(kind='histogram', filename='cufflinks/basic-histogram')


# Customize your histogram with 
# - `barmode` (`overlay` | `group` | `stack`)
# - `bins` (`int`)
# - `histnorm` (`'' | 'percent' | 'probability' | 'density' | 'probability density'`)
# - `histfunc` (`'count' | 'sum' | 'avg' | 'min' | 'max'`)

# In[27]:


df.iplot(kind='histogram', barmode='stack', bins=100, histnorm='probability', filename='cufflinks/customized-histogram')


# Like every chart type, split your traces into subplots or small-multiples with `subplots` and optionally `shape`. More on `subplots` below.

# In[28]:


df.iplot(kind='histogram', subplots=True, shape=(3, 1), filename='cufflinks/histogram-subplots')


# ##### Box Plots

# In[29]:


df = pd.DataFrame(np.random.rand(10, 5), columns=['A', 'B', 'C', 'D', 'E'])
df.iplot(kind='box', filename='cufflinks/box-plots')


# #### Area Charts
# 
# To produce stacked area plot, each column must be either all positive or all negative values.
# 
# When input data contains `NaN`, it will be automatically filled by 0. If you want to drop or fill by different values, use `dataframe.dropna()` or `dataframe.fillna()` before calling plot.

# In[30]:


df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])


# In[31]:


df.iplot(kind='area', fill=True, filename='cuflinks/stacked-area')


# For non-stacked area charts, set `kind=scatter` with `fill=True`

# In[32]:


df.iplot(fill=True, filename='cuflinks/filled-area')


# #### Scatter Plot
# 
# Set `x` and `y` as column names. If `x` isn't supplied, `df.index` will be used.

# In[5]:


import pandas as pd
df = pd.read_csv('http://www.stat.ubc.ca/~jenny/notOcto/STAT545A/examples/gapminder/data/gapminderDataFiveYear.txt', sep='\t')
df2007 = df[df.year==2007]
df1952 = df[df.year==1952]

df2007.iplot(kind='scatter', mode='markers', x='gdpPercap', y='lifeExp', filename='cufflinks/simple-scatter')


# Plotting multiple column scatter plots isn't as easy with cufflinks. Here is an example with Plotly's native syntax

# In[35]:


fig = {
    'data': [
        {'x': df2007.gdpPercap, 'y': df2007.lifeExp, 'text': df2007.country, 'mode': 'markers', 'name': '2007'},
        {'x': df1952.gdpPercap, 'y': df1952.lifeExp, 'text': df1952.country, 'mode': 'markers', 'name': '1952'}
    ],
    'layout': {
        'xaxis': {'title': 'GDP per Capita', 'type': 'log'},
        'yaxis': {'title': "Life Expectancy"}
    }
}
py.iplot(fig, filename='cufflinks/multiple-scatter')


# Grouping isn't as easy either. But, with Plotly's native syntax:

# In[36]:


py.iplot(
    {
        'data': [
            {
                'x': df[df['year']==year]['gdpPercap'],
                'y': df[df['year']==year]['lifeExp'],
                'name': year, 'mode': 'markers',
            } for year in [1952, 1982, 2007]
        ],
        'layout': {
            'xaxis': {'title': 'GDP per Capita', 'type': 'log'},
            'yaxis': {'title': "Life Expectancy"}
        }
}, filename='cufflinks/scatter-group-by')


# #### Bubble Charts
# Add `size` to create a bubble chart. Add hover text with the `text` attribute.

# In[37]:


df2007.iplot(kind='bubble', x='gdpPercap', y='lifeExp', size='pop', text='country',
             xTitle='GDP per Capita', yTitle='Life Expectancy',
             filename='cufflinks/simple-bubble-chart')


# #### Subplots

# `subplots=True` partitions columns into separate subplots. Specify rows and columns with `shape=(rows, cols)` and share axes with `shared_xaxes=True` and `shared_yaxes=True`.

# In[38]:


df=cf.datagen.lines(4)
df.iplot(subplots=True, shape=(4,1), shared_xaxes=True, fill=True, filename='cufflinks/simple-subplots')


# Add subplot titles with `subplot_titles` as a list of titles or `True` to use column names.

# In[39]:


df.iplot(subplots=True, subplot_titles=True, legend=False)


# #### Scatter matrix

# In[40]:


df.scatter_matrix(filename='cufflinks/scatter-matrix-subplot', world_readable=True)


# #### Heatmaps

# In[41]:


cf.datagen.heatmap(20,20).iplot(kind='heatmap',colorscale='spectral',
                                filename='cufflinks/simple-heatmap')


# #### Lines and Shaded Areas
# 
# Use `hline` and `vline` for horizontal and vertical lines.

# In[42]:


df=cf.datagen.lines(3,columns=['a','b','c'])


# In[43]:


df.iplot(hline=[2,4],vline=['2015-02-10'])


# Draw shaded regions with `hspan`

# In[44]:


df.iplot(hspan=[(-1,1),(2,5)], filename='cufflinks/shaded-regions')


# Extra parameters can be passed in the form of dictionaries, width, fill, color, fillcolor, opacity

# In[45]:


df.iplot(vspan={'x0':'2015-02-15','x1':'2015-03-15','color':'rgba(30,30,30,0.3)','fill':True,'opacity':.4}, 
         filename='cufflinks/custom-regions')


# ### Customizing Figures
# 
# `cufflinks` is designed for simple one-line charting with Pandas and Plotly. All of the Plotly chart attributes are not directly assignable in the `df.iplot` call signature.
# 
# To update attributes of a `cufflinks` chart that aren't available, first convert it to a figure (`asFigure=True`), then tweak it, then plot it with `plotly.plotly.iplot`.
# 
# Here is an example of a simple plotly figure. You can find more examples in [our online python documentation](https://plotly.com/python).

# In[46]:


from plotly.graph_objs import *
py.iplot({
    'data': [
        Bar(**{
            'x': [1, 2, 3],
            'y': [3, 1, 5],
            'name': 'first trace',
            'type': 'bar'
        }),
        Bar(**{
            'x': [1, 2, 3],
            'y': [4, 3, 6],
            'name': 'second trace',
            'type': 'bar'
        })
    ],
    'layout': Layout(**{
        'title': 'simple example'
    })
}, filename='cufflinks/simple-plotly-example')


# `cufflinks` generates these figure's that describe plotly graphs. For example, this graph:

# In[48]:


df.iplot(kind='scatter', filename='cufflinks/simple-scatter-example')


# has this description:

# In[49]:


figure = df.iplot(kind='scatter', asFigure=True)
print figure.to_string()


# So, if you want to edit any attribute of a Plotly graph from cufflinks, first convert it to a figure and then edit the figure objects. Let's add a yaxis title, tick suffixes, and new legend names to this example:

# In[50]:


figure['layout']['yaxis1'].update({'title': 'Price', 'tickprefix': '$'})
for i, trace in enumerate(figure['data']):
    trace['name'] = 'Trace {}'.format(i)
    
py.iplot(figure, filename='cufflinks/customized-chart')


# [See more examples of Plotly graphs](https://plotly.com/python/) or [view the entire reference of valid attributes](https://plotly.com/python/reference/)

# #### Cufflinks Reference
# Cufflinks is [open source on github](https://github.com/santosjorge/cufflinks)!

# In[52]:


help(df.iplot)


# In[6]:


#!pip install git+https://github.com/plotly/publisher.git --upgrade
import publisher
publisher.publish(
    'cufflinks.ipynb', 'ipython-notebooks/cufflinks/', 'Cufflinks - Easy Pandas DataFrame Graphing with Plotly | plotly',
    'An overview of cufflinks, a library for easy interactive Pandas charting with Plotly.',
    title = 'Cufflinks - Easy Pandas DataFrame Graphing with Plotly | plotly',
    name = 'Cufflinks',
    thumbnail='thumbnail/line-plot.jpg', language='python',
    ipynb= '~notebook_demo/3')


# In[ ]: