Made output of nearest neighbours downloadable
Browse files- .gitignore +1 -0
- app.py +20 -4
- word2vec.py +15 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
downloads
|
app.py
CHANGED
|
@@ -39,8 +39,7 @@ if active_tab == "Nearest neighbours":
|
|
| 39 |
elif time_slice == 'Late Roman':
|
| 40 |
time_slice = 'late_roman'
|
| 41 |
|
| 42 |
-
time_slice = time_slice.lower() + "_cbow"
|
| 43 |
-
|
| 44 |
|
| 45 |
|
| 46 |
# Check if all fields are filled in
|
|
@@ -56,8 +55,25 @@ if active_tab == "Nearest neighbours":
|
|
| 56 |
nearest_neighbours,
|
| 57 |
columns=["Word", "Time slice", "Similarity"],
|
| 58 |
index = range(1, len(nearest_neighbours) + 1)
|
| 59 |
-
)
|
| 60 |
-
st.table(df)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
# Cosine similarity tab
|
|
|
|
| 39 |
elif time_slice == 'Late Roman':
|
| 40 |
time_slice = 'late_roman'
|
| 41 |
|
| 42 |
+
time_slice = time_slice.lower() + "_cbow"
|
|
|
|
| 43 |
|
| 44 |
|
| 45 |
# Check if all fields are filled in
|
|
|
|
| 55 |
nearest_neighbours,
|
| 56 |
columns=["Word", "Time slice", "Similarity"],
|
| 57 |
index = range(1, len(nearest_neighbours) + 1)
|
| 58 |
+
)
|
| 59 |
+
st.table(df)
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
# Store content in a temporary file
|
| 63 |
+
tmp_file = store_df_in_temp_file(df)
|
| 64 |
+
|
| 65 |
+
# Open the temporary file and read its content
|
| 66 |
+
with open(tmp_file, "rb") as file:
|
| 67 |
+
file_byte = file.read()
|
| 68 |
+
|
| 69 |
+
# Create download button
|
| 70 |
+
st.download_button(
|
| 71 |
+
"Download results",
|
| 72 |
+
data=file_byte,
|
| 73 |
+
file_name = f'nearest_neighbours_{word}_{time_slice}.xlsx',
|
| 74 |
+
mime='application/octet-stream'
|
| 75 |
+
)
|
| 76 |
+
|
| 77 |
|
| 78 |
|
| 79 |
# Cosine similarity tab
|
word2vec.py
CHANGED
|
@@ -2,6 +2,7 @@ from gensim.models import Word2Vec
|
|
| 2 |
from collections import defaultdict
|
| 3 |
import os
|
| 4 |
import tempfile
|
|
|
|
| 5 |
|
| 6 |
|
| 7 |
def load_all_models():
|
|
@@ -249,6 +250,20 @@ def write_to_file(data):
|
|
| 249 |
return temp_file_path
|
| 250 |
|
| 251 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
def main():
|
| 253 |
# model = load_word2vec_model('models/archaic_cbow.model')
|
| 254 |
# archaic_cbow_dict = model_dictionary(model)
|
|
|
|
| 2 |
from collections import defaultdict
|
| 3 |
import os
|
| 4 |
import tempfile
|
| 5 |
+
import pandas as pd
|
| 6 |
|
| 7 |
|
| 8 |
def load_all_models():
|
|
|
|
| 250 |
return temp_file_path
|
| 251 |
|
| 252 |
|
| 253 |
+
def store_df_in_temp_file(df):
|
| 254 |
+
'''
|
| 255 |
+
Store the dataframe in a temporary file
|
| 256 |
+
'''
|
| 257 |
+
# Create random tmp file name
|
| 258 |
+
_, temp_file_path = tempfile.mkstemp(prefix="temp_", suffix=".xlsx", dir="./downloads/nn")
|
| 259 |
+
|
| 260 |
+
# Write data to the temporary file
|
| 261 |
+
with pd.ExcelWriter(temp_file_path, engine='xlsxwriter') as writer:
|
| 262 |
+
df.to_excel(writer, index=False)
|
| 263 |
+
|
| 264 |
+
return temp_file_path
|
| 265 |
+
|
| 266 |
+
|
| 267 |
def main():
|
| 268 |
# model = load_word2vec_model('models/archaic_cbow.model')
|
| 269 |
# archaic_cbow_dict = model_dictionary(model)
|