diff --git a/clean/utils.py b/clean/utils.py
new file mode 100644
index 0000000..e398342
--- /dev/null
+++ b/clean/utils.py
@@ -0,0 +1,65 @@
+
+# Numpy and pandas by default assume a narrow screen - this fixes that
+from fastai2.vision.all import *
+from nbdev.showdoc import *
+from ipywidgets import widgets
+from pandas.api.types import CategoricalDtype
+
+import matplotlib as mpl
+# mpl.rcParams['figure.dpi']= 200
+mpl.rcParams['savefig.dpi']= 200
+mpl.rcParams['font.size']=12
+
+set_seed(42)
+torch.backends.cudnn.deterministic = True
+torch.backends.cudnn.benchmark = False
+pd.set_option('display.max_columns',999)
+np.set_printoptions(linewidth=200)
+torch.set_printoptions(linewidth=200)
+
+import graphviz
+def gv(s): return graphviz.Source('digraph G{ rankdir="LR"' + s + '; }')
+
+def get_image_files_sorted(path, recurse=True, folders=None): return get_image_files(path, recurse, folders).sorted()
+
+
+# +
+# pip install azure-cognitiveservices-search-imagesearch
+
+from azure.cognitiveservices.search.imagesearch import ImageSearchClient as api
+from msrest.authentication import CognitiveServicesCredentials as auth
+
+def search_images_bing(key, term, min_sz=128):
+    client = api('https://api.cognitive.microsoft.com', auth(key))
+    return L(client.images.search(query=term, count=150, min_height=min_sz, min_width=min_sz).value)
+
+
+# -
+
+def plot_function(f, tx=None, ty=None, title=None, min=-2, max=2, figsize=(6,4)):
+    x = torch.linspace(min,max)
+    fig,ax = plt.subplots(figsize=figsize)
+    ax.plot(x,f(x))
+    if tx is not None: ax.set_xlabel(tx)
+    if ty is not None: ax.set_ylabel(ty)
+    if title is not None: ax.set_title(title)
+
+# +
+from sklearn.tree import export_graphviz
+
+def draw_tree(t, df, size=10, ratio=0.6, precision=0, **kwargs):
+    s=export_graphviz(t, out_file=None, feature_names=df.columns, filled=True, rounded=True,
+                      special_characters=True, rotate=False, precision=precision, **kwargs)
+    return graphviz.Source(re.sub('Tree {', f'Tree {{ size={size}; ratio={ratio}', s))
+
+
+# +
+from scipy.cluster import hierarchy as hc
+
+def cluster_columns(df, figsize=(10,6), font_size=12):
+    corr = np.round(scipy.stats.spearmanr(df).correlation, 4)
+    corr_condensed = hc.distance.squareform(1-corr)
+    z = hc.linkage(corr_condensed, method='average')
+    fig = plt.figure(figsize=figsize)
+    hc.dendrogram(z, labels=df.columns, orientation='left', leaf_font_size=font_size)
+    plt.show()