Merge pull request #518 from QuantEcon/add_rank_size

Adds a rank size plot to inequality

Author: mmcky

quantecon/__init__.py

@@ -7,7 +7,8 @@
 	import numba
 except:
 	raise ImportError(
-		"Cannot import numba from current anaconda distribution. Please run `conda install numba` to install the latest version.")
+		"Cannot import numba from current anaconda distribution. \
+			Please run `conda install numba` to install the latest version.")
 
 #-Modules-#
 from . import distributions
@@ -25,7 +26,8 @@
 # from .game_theory import <objects-here> 							#Place Holder if we wish to promote any general objects to the qe namespace.
 from .graph_tools import DiGraph, random_tournament_graph
 from .gridtools import cartesian, mlinspace, simplex_grid, simplex_index
-from .inequality import lorenz_curve, gini_coefficient, shorrocks_index
+from .inequality import lorenz_curve, gini_coefficient, shorrocks_index, \
+	rank_size_plot
 from .kalman import Kalman
 from .lae import LAE
 from .arma import ARMA
@@ -37,7 +39,8 @@
 from .quadsums import var_quadratic_sum, m_quadratic_sum
 #->Propose Delete From Top Level
 #Promote to keep current examples working
-from .markov import MarkovChain, random_markov_chain, random_stochastic_matrix, gth_solve, tauchen, rouwenhorst
+from .markov import MarkovChain, random_markov_chain, random_stochastic_matrix, \
+	gth_solve, tauchen, rouwenhorst
 #Imports that Should be Deprecated with markov package
 from .markov import mc_compute_stationary, mc_sample_path
 #<-

quantecon/inequality.py

@@ -117,3 +117,40 @@ def shorrocks_index(A):
     diag_sum = np.diag(A).sum()
 
     return (m - diag_sum) / (m - 1)
+
+
+def rank_size_plot(data, ax, label=None, c=1.0):
+    """
+    Generate rank-size data corresponding to distribution data.
+
+    Examples
+    --------
+
+    > import numpy as np
+    > import matplotlib.pyplot as plt
+    > y = np.exp(np.random.randn(1000))  # simulate data
+    > fig, ax = plt.subplots()
+    > rank_size_plot(y, ax)
+    > plt.show()
+
+    Parameters
+    ----------
+
+    data : array_like
+        the set of observations
+    c : int or float
+        restrict plot to top (c x 100)% of the distribution
+    ax : axis object
+        for plotting on, has method ax.loglog
+    """
+    w = - np.sort(- data)                  # Reverse sort
+    w = w[:int(len(w) * c)]                # extract top c%
+    rank_data = np.arange(len(w)) + 1
+    size_data = w
+    ax.loglog(rank_data, size_data, 'o', markersize=3.0, alpha=0.5, label=label)
+    if label:
+        ax.legend()
+    ax.set_xlabel("log rank")
+    ax.set_ylabel("log size")
+
+