added a ploting module with a scatter plot function

Author: jshiv

playground/dev/sample_notebook.py

@@ -0,0 +1,63 @@
+
+# coding: utf-8
+
+# In[1]:
+
+##### custome imports
+try:
+    import template
+except Exception as e:
+    print e
+
+##### standard imports
+import pandas as pd
+import numpy as np
+import datetime as dt
+import seaborn as sns
+import pytz
+import matplotlib.pylab as plt
+
+##### globals
+now = dt.datetime.now(pytz.timezone('US/Pacific'))
+datestr = now.strftime('%m%d%y')
+rootdir = './results/'
+
+##### status, ipynb options
+print 'script executed at', now
+pd.set_option('display.max_columns', 500)
+pd.set_option('display.max_rows',    100)
+
+#make the plots happen inline
+get_ipython().magic(u'matplotlib inline')
+
+
+# ## Make a simple matplotlib plot with numpy arrays
+
+# In[2]:
+
+X = np.random.randn(100)
+Y = np.random.randn(100)
+
+plt.scatter(X,Y)
+plt.show()
+
+
+# ## Make a DataFrame
+
+# In[12]:
+
+df = pd.DataFrame({'X':X,'Y':Y})
+df.head()
+
+
+# ##Make a pretty plot with seaborn
+
+# In[14]:
+
+sns.jointplot(X,Y, kind = 'reg' )
+
+
+# In[ ]:
+
+
+

projects/.DS_Store

@@ -0,0 +1,37 @@
+
+# coding: utf-8
+
+# Dont forget to install your package. 
+# 
+# ```
+# python setup.py install
+# ```
+# or on a mac...
+# ```
+# sudo python setup.py install
+# ```
+
+# In[1]:
+
+import template
+
+
+# try using the tab button to see what modules and methods you have avaliable
+
+# In[2]:
+
+template.simple_module
+
+
+# try shit tab after () to see the doc string of the methods you build in simple module
+
+# In[3]:
+
+die = template.simple_module.die(6)
+die.roll()
+
+
+# >In order to make updates to the source code:
+#     1. The source code must be saved.
+#     2. The package must be re-installed with "python setup.py install"
+#     3. The notebook kernal must be restarted

repos/template/ipynbs/using_template.py

@@ -0,0 +1,171 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+
+
+
+def scatter_plot(x, y, data = None, hue = None, title = 'Scatter Plot'
+				 ,xlabel = 'X-Values', ylabel = 'Y-Values', alpha=0.3, figsize=(9.5*1.5,6*1.5), saveAs = None
+				 ,vlines = None, hlines = None
+				 ,xlim = (None,None), ylim = (None,None), legend = True,
+				 model = None,
+				 plotly = False):
+	'''
+	scatter_plot uses matplotlib.pyplot.scatter in a seaborn like functional paridigm
+
+	Parameters
+	----------
+	x, y : strings
+		Column names in ``data``.
+	data : DataFrame
+		Long-form (tidy) dataframe with variables in columns and observations
+		in rows.
+	hue, col, row : strings, optional
+		Variable names to facet on the hue, col, or row dimensions (see
+		:class:`FacetGrid` docs for more information).
+	title, xlabel, ylabel : strings
+		labels of scatter plot.
+	alpha : float
+		opacity of scatter points.
+	figsize : touple, (width, height)
+	saveAs : optional
+		filename to save figure as
+	vlines : list
+		list of x points to make vertical lines in the plot
+	xlim : touple (xmin, xmax)
+		horizontal boundries of the figure
+	ylim : tuple (ymin, ymax)
+		vertical boundries of the plot
+	legend : boolean, optional
+		Draw a legend for the data when using a `hue` variable.
+
+
+	Examples
+	--------
+
+	.. plot:: 
+		>>>import plotBox
+		>>>f = 1000
+		>>>hue = ['one' for i in range(50*f)] + ['two' for i in range(30*f)] + ['three' for i in range(20*f)]
+		>>>plotBox.scatter_plot(x = np.random.randn(100*f), y = np.random.randn(100*f), hue = hue, vlines = 0, alpha= .1, hlines = 0)
+	
+	.. todo::
+
+		Add arguments:
+
+		* dropna : boolean, optional
+		Drop missing values from the data before plotting.
+
+		* add regression : 
+		f, popt, pcov = rp.statBox.regression_model(x,y, model)
+		plt.plot(np.linspace(0,max(x)+100,50), f(np.linspace(0,max(x)+100,50), *popt), 'r-', label="Fitted Curve")
+
+
+	Notes
+	-----
+	This function can be used in 2 different ways:
+
+		* Using the arguments to generate titles, legends, etc... and then save/display the plot 
+
+		* Incorporate the plot in a script and overriding the plotting features this way:
+
+			>>> import matplotlib.pyplot as plt 
+			>>>
+			>>> f = 1000
+			>>> hue = ['one' for i in range(50*f)] + ['two' for i in range(30*f)] + ['three' for i in range(20*f)]
+			>>> plotBox.scatter_plot(x = np.random.randn(100*f), y = np.random.randn(100*f), hue = hue, vlines = 0, alpha= .1, hlines = 0)
+			>>> plt.title('My title')
+			>>> plt.xlabel('X label I want')
+			>>>
+			>>> # To change the figure size :
+			>>> fig = plt.gcf()	# get the figure object
+			>>> fig.set_size_inches(5,10)
+			>>>
+			>>> plt.show()
+
+	'''
+
+	if isinstance(x, basestring):
+		if xlabel == 'X-Values':
+			xlabel = x
+		x = list(data[x])
+	else:
+		x = list(x)
+
+	if isinstance(y, basestring):
+		if ylabel == 'Y-Values':
+			ylabel = y
+		y = list(data[y])
+	else:
+		y = list(y)
+
+
+	if hue is None:
+		hue = ['Data' for i in range(len(x))]
+	else:
+		if isinstance(hue, basestring):
+			hue = list(data[hue])
+		else:
+			hue = list(hue)   
+
+	hue_count_set = []
+	for h in set(hue):
+		hue_count_set.append((hue.count(h),h))
+
+	hue_labels = [t[1] for t in sorted(hue_count_set, reverse = True)]
+
+
+	if len(hue_labels) > 7:
+		color_list = list(np.random.rand(len(hue_labels)))
+	else:
+		color_list = ['c','r','g','b','m','y','k'] 
+	inc = 0
+	fig = plt.figure(figsize = figsize)
+	for h in hue_labels:
+		idx = list(np.where(np.array(hue) == h)[0])
+		x_idx = [x[i] for i in idx]
+		y_idx = [y[i] for i in idx]
+		plt.scatter(x_idx, y_idx, c = color_list[inc], alpha=alpha)
+		inc += 1
+
+	if legend:
+		plt.legend(hue_labels) 
+	plt.title(title, size = 16)
+	plt.xlabel(xlabel, fontsize = 14)
+	plt.ylabel(ylabel, fontsize = 14)
+
+	if ylim[0] is None:
+		y_min = plt.ylim()[0]
+	else:
+		y_min = ylim[0]
+
+	if ylim[1] is None:
+		y_max = plt.ylim()[1]
+	else:
+		y_max = ylim[1]
+	plt.ylim(y_min, y_max)
+
+
+	if xlim[0] is None:
+		x_min = plt.xlim()[0]
+	else:
+		x_min = xlim[0]
+
+	if xlim[1] is None:
+		x_max = plt.xlim()[1]
+	else:
+		x_max = xlim[1]
+	plt.xlim(x_min, x_max)
+
+
+	if vlines is not None:
+		plt.vlines(vlines, y_min, y_max)
+	if hlines is not None:
+		plt.hlines(hlines, x_min, x_max)
+
+	# if plotly:
+	# 	plot_url = py.iplot_mpl(fig, filename=title, fileopt='overwrite')
+
+	if saveAs is not None:
+		plt.savefig(saveAs)
+