about summary refs log tree commit diff
path: root/users/wpcarro/scratch/facebook/word-cloud.py
diff options
context:
space:
mode:
authorVincent Ambo <mail@tazj.in>2021-12-13T22·51+0300
committerVincent Ambo <mail@tazj.in>2021-12-13T23·15+0300
commit019f8fd2113df4c5247c3969c60fd4f0e08f91f7 (patch)
tree76a857f61aa88f62a30e854651e8439db77fd0ea /users/wpcarro/scratch/facebook/word-cloud.py
parent464bbcb15c09813172c79820bcf526bb10cf4208 (diff)
parent6123e976928ca3d8d93f0b2006b10b5f659eb74d (diff)
subtree(users/wpcarro): docking briefcase at '24f5a642' r/3226
git-subtree-dir: users/wpcarro
git-subtree-mainline: 464bbcb15c09813172c79820bcf526bb10cf4208
git-subtree-split: 24f5a642af3aa1627bbff977f0a101907a02c69f
Change-Id: I6105b3762b79126b3488359c95978cadb3efa789
Diffstat (limited to 'users/wpcarro/scratch/facebook/word-cloud.py')
-rw-r--r--users/wpcarro/scratch/facebook/word-cloud.py32
1 files changed, 32 insertions, 0 deletions
diff --git a/users/wpcarro/scratch/facebook/word-cloud.py b/users/wpcarro/scratch/facebook/word-cloud.py
new file mode 100644
index 0000000000..88422e3631
--- /dev/null
+++ b/users/wpcarro/scratch/facebook/word-cloud.py
@@ -0,0 +1,32 @@
+def normalize(x):
+    noise = ".,;-"
+    for y in noise:
+        if x.endswith(y):
+            return normalize(x[0:-1])
+        if x.startswith(y):
+            return normalize(x[1:])
+    return x.lower()
+
+def word_cloud(xs):
+    result = dict()
+
+    for x in xs.split(' '):
+        k = normalize(x)
+        if k in result:
+            result[k] += 1
+        else:
+            result[k] = 1
+
+    return result
+
+result = word_cloud("This is just the beginning. The UK will lockdown again.")
+assert result.get('this') == 1
+assert result.get('is') == 1
+assert result.get('just') == 1
+assert result.get('the') == 2
+assert result.get('beginning') == 1
+assert result.get('uk') == 1
+assert result.get('will') == 1
+assert result.get('lockdown') == 1
+assert result.get('again') == 1
+print("Success!")