Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -71,6 +71,10 @@ import base64
|
|
| 71 |
#for PDF form filling
|
| 72 |
from PyPDFForm import FormWrapper
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
#Variables Initialization
|
| 75 |
agent_executor = None
|
| 76 |
vector_store1 = None
|
|
@@ -1152,12 +1156,8 @@ def handle_large_dataset(df, create_document,isDataFrame):
|
|
| 1152 |
docstatus = f"Download the complete dataset <a href='https://redmindtechnologies.com/RedMindGPT/output.xlsx' download> here.</a>.There are total of {total_rows} rows."
|
| 1153 |
if total_rows < 4000:
|
| 1154 |
|
| 1155 |
-
# 1. Limit to first 10 rows
|
| 1156 |
|
| 1157 |
-
|
| 1158 |
-
# 2. Handle missing values
|
| 1159 |
-
#limited_data.fillna("N/A", inplace=True)
|
| 1160 |
-
# 3. Drop the original first column
|
| 1161 |
if len(df.columns) > 1:
|
| 1162 |
# Skipping the original first column
|
| 1163 |
limited_data = df.head(3)
|
|
@@ -1165,8 +1165,8 @@ def handle_large_dataset(df, create_document,isDataFrame):
|
|
| 1165 |
else:
|
| 1166 |
limited_data = df.head(20)
|
| 1167 |
limited_data_without_first_column = limited_data
|
| 1168 |
-
|
| 1169 |
-
#
|
| 1170 |
if isDataFrame :
|
| 1171 |
|
| 1172 |
limited_data_without_first_column.insert(0, 'SNo', range(1, len(limited_data_without_first_column) + 1))
|
|
@@ -1176,10 +1176,6 @@ def handle_large_dataset(df, create_document,isDataFrame):
|
|
| 1176 |
# 3. Save the full dataset to a downloadable file
|
| 1177 |
|
| 1178 |
|
| 1179 |
-
import os
|
| 1180 |
-
|
| 1181 |
-
# Get the current working directory
|
| 1182 |
-
current_folder = os.getcwd()
|
| 1183 |
|
| 1184 |
|
| 1185 |
file_path = "output_data.xlsx"
|
|
@@ -1187,8 +1183,8 @@ def handle_large_dataset(df, create_document,isDataFrame):
|
|
| 1187 |
df.to_excel(file_path, index=False)
|
| 1188 |
|
| 1189 |
|
| 1190 |
-
|
| 1191 |
-
|
| 1192 |
global user_name
|
| 1193 |
# Get today's date and current time
|
| 1194 |
now = datetime.now()
|
|
@@ -1228,9 +1224,7 @@ def create_file_HF(file_path,directory):
|
|
| 1228 |
|
| 1229 |
api = HfApi()
|
| 1230 |
|
| 1231 |
-
repo_id = "Redmind/NewageNXTGPT_Repo_trial"
|
| 1232 |
-
|
| 1233 |
-
|
| 1234 |
|
| 1235 |
|
| 1236 |
|
|
@@ -1240,7 +1234,7 @@ def create_file_HF(file_path,directory):
|
|
| 1240 |
directory = directory + "/" + file_path
|
| 1241 |
else:
|
| 1242 |
directory = directory + "/" + file_path
|
| 1243 |
-
|
| 1244 |
|
| 1245 |
#create_branch("Redmind/NewageNXTGPT_Repo_trial", repo_type="space", branch="test-branch")
|
| 1246 |
|
|
@@ -1268,11 +1262,7 @@ def create_pdf(cname,ename,account_number, directory):
|
|
| 1268 |
output.write(filled.read())
|
| 1269 |
create_file_HF(output_file_name, directory)
|
| 1270 |
|
| 1271 |
-
|
| 1272 |
-
file_output=f"static/{output_file_name}"
|
| 1273 |
-
from huggingface_hub import HfApi
|
| 1274 |
-
api = HfApi()
|
| 1275 |
-
#api.upload_file(path_or_fileobj=output_file_name, repo_id=repo_id, repo_type= "space", path_in_repo=file_output)
|
| 1276 |
return f"{output_file_name} is created successfully."
|
| 1277 |
|
| 1278 |
|
|
|
|
| 71 |
#for PDF form filling
|
| 72 |
from PyPDFForm import FormWrapper
|
| 73 |
|
| 74 |
+
import os
|
| 75 |
+
|
| 76 |
+
# Get the current working directory
|
| 77 |
+
current_folder = os.getcwd()
|
| 78 |
#Variables Initialization
|
| 79 |
agent_executor = None
|
| 80 |
vector_store1 = None
|
|
|
|
| 1156 |
docstatus = f"Download the complete dataset <a href='https://redmindtechnologies.com/RedMindGPT/output.xlsx' download> here.</a>.There are total of {total_rows} rows."
|
| 1157 |
if total_rows < 4000:
|
| 1158 |
|
|
|
|
| 1159 |
|
| 1160 |
+
# 1. Drop the original first column
|
|
|
|
|
|
|
|
|
|
| 1161 |
if len(df.columns) > 1:
|
| 1162 |
# Skipping the original first column
|
| 1163 |
limited_data = df.head(3)
|
|
|
|
| 1165 |
else:
|
| 1166 |
limited_data = df.head(20)
|
| 1167 |
limited_data_without_first_column = limited_data
|
| 1168 |
+
|
| 1169 |
+
# 2. Add SNo (serial number) as the first column, starting from 1
|
| 1170 |
if isDataFrame :
|
| 1171 |
|
| 1172 |
limited_data_without_first_column.insert(0, 'SNo', range(1, len(limited_data_without_first_column) + 1))
|
|
|
|
| 1176 |
# 3. Save the full dataset to a downloadable file
|
| 1177 |
|
| 1178 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1179 |
|
| 1180 |
|
| 1181 |
file_path = "output_data.xlsx"
|
|
|
|
| 1183 |
df.to_excel(file_path, index=False)
|
| 1184 |
|
| 1185 |
|
| 1186 |
+
|
| 1187 |
+
|
| 1188 |
global user_name
|
| 1189 |
# Get today's date and current time
|
| 1190 |
now = datetime.now()
|
|
|
|
| 1224 |
|
| 1225 |
api = HfApi()
|
| 1226 |
|
| 1227 |
+
repo_id = "Redmind/NewageNXTGPT_Repo_trial"
|
|
|
|
|
|
|
| 1228 |
|
| 1229 |
|
| 1230 |
|
|
|
|
| 1234 |
directory = directory + "/" + file_path
|
| 1235 |
else:
|
| 1236 |
directory = directory + "/" + file_path
|
| 1237 |
+
|
| 1238 |
|
| 1239 |
#create_branch("Redmind/NewageNXTGPT_Repo_trial", repo_type="space", branch="test-branch")
|
| 1240 |
|
|
|
|
| 1262 |
output.write(filled.read())
|
| 1263 |
create_file_HF(output_file_name, directory)
|
| 1264 |
|
| 1265 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1266 |
return f"{output_file_name} is created successfully."
|
| 1267 |
|
| 1268 |
|