1.9.3 Feature Update

- added a world map heatmap
- added shapes files for the world map
- cleaned up imports from several files
- added a counties csv with country codes, regions, etc.
- added a function for coverting country <-> codes
- improved corr() so that it supports many more variables
- corr() automatically adjusts size based on number of features
- line() takes all features in dataframe except 'y' if 'x' is left None
- swallow the warning from statsmodels for FutureWarning of pandas datetime
- added an exception for MissingImport
- updated requirements.txt
- reorganized dependcy installs in setup.py
- added .pyc files to .gitignore
- added possibility to input labels to line() >> this needs to be in all the plots
- added outlier filtering to world() >> this needs to be in all the plots
- fixed issue #15 regarding default x and y limit settings for plots
- small cleanups throughout all the plots
- added many example plots

.gitignore

@@ -1,2 +1,3 @@
 .DS_Store
+*.pyc
 __pycache__

astetik/__init__.py

@@ -19,6 +19,7 @@
 from .plots.bar import bar
 from .plots.bartwo import bartwo
 from .plots.animate import Animation
+from .plots.world import world
 # from .plots.words import words
 
 
@@ -28,6 +29,6 @@
 from .tables.text import text
 # from .tables.timeseries import timeseries
 
-from .utils.transform import boolcols_to_cat
+del plots, style, tables, utils
 
-__version__ = "1.9.2"
+__version__ = "1.9.3"

astetik/plots/__init__.py

@@ -1 +1 @@
-__version__ = "1.9.2"
+__version__ = "1.9.3"

astetik/plots/animate.py

@@ -1,6 +1,8 @@
 import glob
 import os
 import numpy as np
+# EXCEPTIONAL IMPORT #
+
 import matplotlib.pyplot as plt
 
 from IPython.display import clear_output

astetik/plots/bar.py

@@ -1,13 +1,8 @@
-# EXCEPTIONAL IMPORT #
-import matplotlib
-matplotlib.use('Agg')
-# ENDS #
-
 import seaborn as sns
 import pandas as pd
 
 from ..style.template import _header, _footer
-from ..utils.utils import _limiter, _scaler
+from ..utils.utils import _scaler
 from ..utils.utils import factorplot_sizing
 from ..style.titles import _titles
 
@@ -28,8 +23,8 @@ def bar(data,
         legend=True,
         x_scale='linear',
         y_scale='linear',
-        x_limit='auto',
-        y_limit='auto',
+        x_limit=None,
+        y_limit=None,
         save=False):
 
     '''BAR PLOT

astetik/plots/bargrid.py

@@ -1,14 +1,7 @@
-# EXCEPTIONAL IMPORT #
-import matplotlib
-matplotlib.use('Agg')
-# ENDS #
-
-import matplotlib.pyplot as plt
-from matplotlib.pyplot import rcParams
 import seaborn as sns
 
 from ..style.template import _header, _footer
-from ..utils.utils import _limiter, _scaler
+from ..utils.utils import _scaler
 
 
 def bargrid(data,
@@ -28,8 +21,8 @@ def bargrid(data,
             legend=True,
             x_scale='linear',
             y_scale='linear',
-            x_limit='auto',
-            y_limit='auto',
+            x_limit=None,
+            y_limit=None,
             save=False):
 
     '''BAR PLOT

astetik/plots/bartwo.py

@@ -1,13 +1,7 @@
-# EXCEPTIONAL IMPORT #
-import matplotlib
-matplotlib.use('Agg')
-# ENDS #
-
 import seaborn as sns
-import pandas as pd
 
 from ..style.template import _header, _footer
-from ..utils.utils import _limiter, _scaler
+from ..utils.utils import _scaler
 from ..utils.utils import factorplot_sizing
 from ..style.titles import _titles
 
@@ -29,20 +23,16 @@ def bartwo(data,
            legend=True,
            x_scale='linear',
            y_scale='linear',
-           x_limit='auto',
-           y_limit='auto',
+           x_limit=None,
+           y_limit=None,
            save=False):
 
     '''2-D BAR PLOT
 
     A 2-dimensional bar graph for the case where there is a continuous
-    variable that is compared against labels and a single categorial.
-
-is a single
-    value per label. Accepts either dataframe or series. If series,
-    then labels will come from index.
-
-    Inputs: 1 (Series), 2(DataFrame)
+    variable that is compared against labels and a single categorial. The
+    'x' is the continuous variable, 'y' is the labels (categorical) and
+    'hue' is the comparison color.
 
     1. USE
     ======
@@ -56,9 +46,11 @@ def bartwo(data,
     --------------------
     data :: pandas dataframe
 
-    x :: x-axis data (single value per label)
+    x :: x-axis data (continuous)
+
+    y :: y-axis data (category labels)
 
-    y :: y-axis data (labels)
+    hue :: color comparison data (preferably binary categorical)
 
     --------------------
     2.2. PLOT PARAMETERS

astetik/plots/box.py

@@ -22,8 +22,8 @@ def box(data,
         legend=True,
         x_scale='linear',
         y_scale='linear',
-        x_limit='auto',
-        y_limit='auto',
+        x_limit=None,
+        y_limit=None,
         save=False):
 
     '''BOX PLOT
@@ -131,8 +131,6 @@ def box(data,
     if x_scale != 'linear' or y_scale != 'linear':
         _scaler(p, x_scale, y_scale)
 
-    _thousand_sep(p, ax)
-
     if x_limit != None or y_limit != None:
         _limiter(data=data, x=x, y=y, x_limit=None, y_limit=y_limit)
     # <<< SCALING AND LIMITS ENDS

astetik/plots/compare.py

@@ -21,8 +21,8 @@ def compare(data,
             legend=True,
             x_scale='linear',
             y_scale='linear',
-            x_limit='auto',
-            y_limit='auto',
+            x_limit=None,
+            y_limit=None,
             save=False):
 
     '''COMPARE PLOT

astetik/plots/corr.py

@@ -1,9 +1,16 @@
+import warnings
+warnings.filterwarnings("ignore")
+
 import numpy as np
-import seaborn as sns
+import matplotlib
+matplotlib.use('Agg')
+# ENDS #
 import matplotlib.pyplot as plt
+import seaborn as sns
+
+
 
 from ..style.formats import _thousand_sep
-from ..style.style import params
 from ..style.titles import _titles
 from ..style.template import _header, _footer
 
@@ -12,8 +19,10 @@ def corr(data,
          corr_method='spearman',
          annot=False,
          mask=True,
-         line_width=2,
-         line_color='white',
+         line_width=1,
+         line_color='black',
+         color_grades=5,
+         auto_sizing=True,
          palette='default',
          style='astetik',
          dpi=72,
@@ -24,14 +33,14 @@ def corr(data,
          legend=True,
          x_scale='linear',
          y_scale='linear',
-         x_limit='auto',
-         y_limit='auto',
+         x_limit=None,
+         y_limit=None,
          save=False):
 
     '''CORRELATION HEATMAP
 
-    This is best used with less than 10 variables in the datasetself.
-    For best results, split the analysis to several parts.
+    This is best used with less than 50 variables in the dataset.
+    For best results, column labels should be clear and not too long.
 
    Inputs: a dataframe with several columns
    Features: Both categorical and continuous features will be used
@@ -74,6 +83,14 @@ def corr(data,
                   to set small when there are really many items.
 
     line_color :: the color of the lines between the elements e.g. 'black'
+
+    auto_sizing :: If not True, then should be int value in inches which is used
+                   for both width and height.
+
+    color_grades :: The number of colors/shades to use in total. 5 is default.
+                    Generally the best results come with 3 or 5 or 7, but looks
+                    better with more colors.
+
     ----------------------
     2.3. COMMON PARAMETERS
     ----------------------
@@ -126,31 +143,34 @@ def corr(data,
     if mask == True:
         mask = np.zeros_like(data)
         mask[np.triu_indices_from(mask)] = True
+        line_color = 'white'
     else:
         mask = None
     # # # # # PREP ENDS # # # # #
 
     # HEADER STARTS >>>
     palette = _header(palette,
                       style,
-                      n_colors=10,
+                      n_colors=color_grades,
                       dpi=dpi)
 
+    if auto_sizing == True:
+        size = data.shape[0] / 2 + 5
+
     # PLOT
-    p, ax = plt.subplots(figsize=(params()['fig_width'],
-                                  params()['fig_height']))
+    p, ax = plt.subplots(figsize=(size, size))
 
     p = sns.heatmap(data,
                     mask=mask,
                     linewidths=line_width,
                     linecolor=line_color,
                     cmap=palette,
-                    annot=annot,
-                    square=True)
+                    annot=annot)
 
     # HEADER
     _thousand_sep(p, ax)
     _titles(title, sub_title=sub_title)
     _footer(p, x_label, y_label, save=save, tight=False, despine=False)
 
-    p.set_xticklabels(data)
+    p.set_xticklabels(data, rotation=90)
+    p.set_yticklabels(data, rotation=0)

astetik/plots/count.py

@@ -19,8 +19,8 @@ def count(data,
           legend=True,
           x_scale='linear',
           y_scale='linear',
-          x_limit='auto',
-          y_limit='auto',
+          x_limit=None,
+          y_limit=None,
           save=False):
 
     '''COUNT PLOT

astetik/plots/grid.py

@@ -19,8 +19,8 @@ def grid(data,
          legend=True,
          x_scale='linear',
          y_scale='linear',
-         x_limit='auto',
-         y_limit='auto',
+         x_limit=None,
+         y_limit=None,
          save=False):
 
     '''THE GRID
@@ -47,9 +47,9 @@ def grid(data,
     --------------------
     data :: pandas dataframe
 
-    x :: x-axis data (categorical)
+    x :: x-axis data (continuous or categorical)
 
-    y :: y-axis data (continuous or categorical)
+    y :: y-axis data (continuous)
 
     hue :: color highlight (categorical)
 
@@ -108,9 +108,11 @@ def grid(data,
     '''
 
     data = data.copy(deep=True)
-    n_colors = 1
-    if hue is True:
-        hue = len(data[hue].unique())
+
+    if hue != None:
+        n_colors = len(data[hue].unique())
+    else:
+        n_colors = 1
 
     # HEADER STARTS >>>
     palette = _header(palette,

astetik/plots/hist.py

@@ -26,8 +26,8 @@ def hist(data,
          legend=False,
          x_scale='linear',
          y_scale='linear',
-         x_limit='auto',
-         y_limit='auto',
+         x_limit=None,
+         y_limit=None,
          save=False):
 
     '''HISTOGRAM
@@ -111,7 +111,7 @@ def hist(data,
     warnings.simplefilter("ignore")
 
     if bins == True:
-        bins = int(len(data[x].unique()) / 10)
+        bins = int(len(data[x].unique()) / 10) + 5
 
     if dropna is True:
         data = data[data[x].isna() == False]

astetik/plots/kde.py

@@ -1,4 +1,3 @@
-
 import seaborn as sns
 import matplotlib.pyplot as plt