Change signature of get_data, use more often

Author: ColCarroll

docs/source/notebooks/GLM.ipynb

@@ -1,33 +1,33 @@
-import pkgutil
-import io
 from copy import copy
+import io
+import os
+import pkgutil
+
 import numpy as np
+import pymc3 as pm
 import theano.tensor as tt
 import theano
-import pymc3 as pm
 
 __all__ = [
-    'get_data_file',
+    'get_data',
     'GeneratorAdapter',
     'DataSampler'
 ]
 
 
-def get_data_file(pkg, path):
-    """Returns a file object for a package data file.
+def get_data(filename):
+    """Returns a BytesIO object for a package data file.
 
     Parameters
     ----------
-    pkg : str
-        dotted package hierarchy. e.g. "pymc3.examples"
-    path : str 
-        file path within package. e.g. "data/wells.dat"
-    Returns 
+    filename : str
+        file to load
+    Returns
     -------
     BytesIO of the data
     """
-
-    return io.BytesIO(pkgutil.get_data(pkg, path))
+    data_pkg = 'pymc3.examples'
+    return io.BytesIO(pkgutil.get_data(data_pkg, os.path.join('data', filename)))
 
 
 class GenTensorVariable(tt.TensorVariable):

docs/source/notebooks/dawid-skene.ipynb

@@ -2,10 +2,10 @@
 import pandas as pd
 import matplotlib.pyplot as plt
 
-from pymc3 import HalfCauchy, Model, Normal, get_data_file, sample
+from pymc3 import HalfCauchy, Model, Normal, get_data, sample
 from pymc3.distributions.timeseries import GaussianRandomWalk
 
-data = pd.read_csv(get_data_file('pymc3.examples', 'data/pancreatitis.csv'))
+data = pd.read_csv(get_data('pancreatitis.csv'))
 countries = ['CYP', 'DNK', 'ESP', 'FIN', 'GBR', 'ISL']
 data = data[data.area.isin(countries)]
 

docs/source/notebooks/hierarchical_partial_pooling.ipynb

@@ -7,7 +7,7 @@
 import numpy as np
 import theano
 
-data = np.loadtxt( 'data/efron-morris-75-data.tsv', delimiter="\t", skiprows=1, usecols=(2,3) )
+data = np.loadtxt(pm.get_data('efron-morris-75-data.tsv'), delimiter="\t", skiprows=1, usecols=(2,3))
 
 atBats = data[:,0].astype(theano.config.floatX)
 hits = data[:,1].astype(theano.config.floatX)
@@ -35,4 +35,3 @@ def run( n=100000 ):
 
 if __name__ == '__main__':
     run()
-

docs/source/notebooks/profiling.ipynb

@@ -3,8 +3,7 @@
 from numpy.ma import masked_values
 
 # Import data, filling missing values with sentinels (-999)
-test_scores = pd.read_csv(pm.get_data_file(
-    'pymc3.examples', 'data/test_scores.csv')).fillna(-999)
+test_scores = pd.read_csv(pm.get_data('test_scores.csv')).fillna(-999)
 
 # Extract variables: test score, gender, number of siblings, previous disability, age,
 # mother with HS education or better, hearing loss identified by 3 months

pymc3/data.py

@@ -12,8 +12,8 @@
 
 def get_city_data():
     """Helper to get city data"""
-    data = pd.read_csv(pm.get_data_file('pymc3.examples', 'data/srrs2.dat'))
-    cty_data = pd.read_csv(pm.get_data_file('pymc3.examples', 'data/cty.dat'))
+    data = pd.read_csv(pm.get_data('srrs2.dat'))
+    cty_data = pd.read_csv(pm.get_data('cty.dat'))
 
     data = data[data.state == 'MN']
 
@@ -30,8 +30,8 @@ def get_city_data():
 
 class TestARM5_4(SeededTest):
     def build_model(self):
-        wells = pm.get_data_file('pymc3.examples', 'data/wells.dat')
-        data = pd.read_csv(wells, delimiter=u' ', index_col=u'id', dtype={u'switch': np.int8})
+        data = pd.read_csv(pm.get_data('wells.dat'),
+                           delimiter=u' ', index_col=u'id', dtype={u'switch': np.int8})
         data.dist /= 100
         data.educ /= 4
         col = data.columns