Create app.py

app.py

@@ -0,0 +1,55 @@
+
+
+import pickle
+import gib_detect_train
+
+model_data = pickle.load(open('gib_model.pki', 'rb'))
+
+
+import math
+import pickle
+
+accepted_chars = 'abcdefghijklmnopqrstuvwxyz '
+
+pos = dict([(char, idx) for idx, char in enumerate(accepted_chars)])
+
+
+def normalize(line):
+    """ Return only the subset of chars from accepted_chars.
+    This helps keep the  model relatively small by ignoring punctuation, 
+    infrequently symbols, etc. """
+    return [c.lower() for c in line if c.lower() in accepted_chars]
+
+
+def ngram(n, l):
+    """ Return all n grams from l after normalizing """
+    filtered = normalize(l)
+    for start in range(0, len(filtered) - n + 1):
+        yield ''.join(filtered[start:start + n])
+
+
+def get_lines():
+    datasets = ['big.txt']
+    for filename in datasets:
+        with open(filename) as fp:
+            for line in fp:
+                yield line
+
+
+def avg_transition_prob(l, log_prob_mat):
+    """ Return the average transition prob from l through log_prob_mat. """
+    log_prob = 0.0
+    transition_ct = 0
+    for a, b, c in ngram(3, l):
+        log_prob += log_prob_mat[pos[a]][pos[b]][pos[c]]
+        transition_ct += 1
+    # The exponentiation translates from log probs to probs.
+    return math.exp(log_prob / (transition_ct or 1))
+    # The exponentiation translates from log probs to probs.
+    return math.exp(log_prob / (transition_ct or 1))
+
+while True:
+    l = st.text_area('enter a prospection message')
+    model_mat = model_data['mat']
+    threshold = model_data['thresh']
+    st.write(avg_transition_prob(l, model_mat) > threshold)