Commit
•
ee8a91d
1
Parent(s):
bd550e0
more performance improvements
Browse files
interpretable_text_clustering.py
CHANGED
@@ -40,7 +40,7 @@ task = form.radio("Which task are we solving?", ('Classification', 'Clustering')
|
|
40 |
dataset_name = form.text_area("Enter the name of the huggingface Dataset to do analysis of:", value = "Hellisotherpeople/DebateSum")
|
41 |
dataset_name_2 = form.text_area("Enter the name of the config for the dataset if it has one", value = "")
|
42 |
split_name = form.text_area("Enter the name of the split of the dataset that you want to use", value = "train")
|
43 |
-
number_of_records = form.number_input("Enter the number of documents that you want to analyze from the dataset", value =
|
44 |
column_name = form.text_area("Enter the name of the column that we are doing analysis on (the X value)", value = "Full-Document")
|
45 |
|
46 |
if task == "Classification":
|
@@ -141,7 +141,7 @@ text_example = """Judge Leon last week questioned the effectiveness of the gover
|
|
141 |
form_explainer = st.sidebar.form("explainer_form")
|
142 |
form_explainer.header("Explainer Settings")
|
143 |
position_dep = form_explainer.checkbox("Check this if you want to take into account the position of a word in the interpretation", value = False)
|
144 |
-
number_samples = form_explainer.number_input("Enter the number of explainer peterbuted samples, higher creates a better explanation but takes longer", value =
|
145 |
char_based = form_explainer.checkbox("Check this if you want to use a character based explanier", value = False)
|
146 |
form_explainer.form_submit_button("Submit")
|
147 |
|
@@ -150,7 +150,7 @@ te = TextExplainer(random_state=42, char_based=char_based, n_samples = number_sa
|
|
150 |
|
151 |
input_choice = st.checkbox("Check this if you want to enter your own example to explain", value = False)
|
152 |
if input_choice == False:
|
153 |
-
record_to_explain = st.number_input("Enter the index of the document from the original dataset to interpret", value =
|
154 |
te.fit(df[column_name][record_to_explain], text_clf.predict_proba)
|
155 |
if task == "Classification":
|
156 |
st.write("Ground truth label")
|
|
|
40 |
dataset_name = form.text_area("Enter the name of the huggingface Dataset to do analysis of:", value = "Hellisotherpeople/DebateSum")
|
41 |
dataset_name_2 = form.text_area("Enter the name of the config for the dataset if it has one", value = "")
|
42 |
split_name = form.text_area("Enter the name of the split of the dataset that you want to use", value = "train")
|
43 |
+
number_of_records = form.number_input("Enter the number of documents that you want to analyze from the dataset", value = 50)
|
44 |
column_name = form.text_area("Enter the name of the column that we are doing analysis on (the X value)", value = "Full-Document")
|
45 |
|
46 |
if task == "Classification":
|
|
|
141 |
form_explainer = st.sidebar.form("explainer_form")
|
142 |
form_explainer.header("Explainer Settings")
|
143 |
position_dep = form_explainer.checkbox("Check this if you want to take into account the position of a word in the interpretation", value = False)
|
144 |
+
number_samples = form_explainer.number_input("Enter the number of explainer peterbuted samples, higher creates a better explanation but takes longer", value = 1000)
|
145 |
char_based = form_explainer.checkbox("Check this if you want to use a character based explanier", value = False)
|
146 |
form_explainer.form_submit_button("Submit")
|
147 |
|
|
|
150 |
|
151 |
input_choice = st.checkbox("Check this if you want to enter your own example to explain", value = False)
|
152 |
if input_choice == False:
|
153 |
+
record_to_explain = st.number_input("Enter the index of the document from the original dataset to interpret", value = 30)
|
154 |
te.fit(df[column_name][record_to_explain], text_clf.predict_proba)
|
155 |
if task == "Classification":
|
156 |
st.write("Ground truth label")
|