Update censusdata readability per issue#5

censusdata_package_tutorial/Help_Functions.py

@@ -27,3 +27,26 @@ def census_cut(tracts, data):
     len(mask), len(data.index)
     result = data[mask]
     return result
+
+
+def data_split(data):
+    
+    data_dict = {}
+    for row in data.index:
+        split_row = re.split('> |, ', str(row))[:-1]
+        data_dict[str(row)] = split_row
+        
+    data_ref = pd.DataFrame.from_dict(data_dict, orient='index', columns=['Block Group', 'Census Tract', 'County', 'State: Summary Level', 'State Code', 'County Code', 'Tract'])
+    data_ref['TOTAL POPULATION'] = 0
+    
+    data_ref['Block Group'] = data_ref['Block Group'].apply(lambda x: int(x.split()[-1]))
+    data_ref['Census Tract'] = data_ref['Census Tract'].apply(lambda x: float(x.split()[-1]))
+    data_ref['State: Summary Level'] = data_ref['State: Summary Level'].apply(lambda x: [x.split(':')[i] for i in (0, -1)])
+    data_ref['State Code'] = data_ref['State Code'].apply(lambda x: int(x.split(':')[-1]))
+    data_ref['County Code'] = data_ref['County Code'].apply(lambda x: int(x.split(':')[-1]))
+    data_ref['Tract'] = data_ref['Tract'].apply(lambda x: int(x.split(':')[-1]))
+    
+    
+    return data_ref
+# -
+