feat: streamlit-app

src/app.py

@@ -0,0 +1,40 @@
+######################################## IMPORTING REQUIRED LIBRARIES ####################################
+import os
+import sys
+import pandas as pd
+import streamlit as st
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+data_folder = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'data')
+from utilities import get_data, input_filter, clean_data, autogenerate_labels
+
+def data_sourcing(left_lat, left_lon, dist, loc_name):
+    lat, lon = input_filter(lat = left_lat, lon=left_lon)
+    df = get_data(lat, lon, dist)
+    df.to_csv(f'{data_folder}/LOCATION_{loc_name}_DATA.csv', index=False)
+    return df
+
+def data_clean_for_training(df):
+    df = clean_data(df)
+    df.to_csv(f'{data_folder}/MMR_DATA_CLEAN.csv', index=False)
+    return df
+
+st.title("Map Data Analysis - ETL Pipeline")
+
+left_lat = st.number_input("Enter the left latitude", value=18.889833)
+left_lon = st.number_input("Enter the left longitude", value=72.779844)
+print(left_lat, left_lon)
+loc_name = st.text_input("Enter the location name", value="Mumbai")
+dist = st.number_input("Enter the distance", value=35)
+
+if st.button("Run ETL Pipeline"):
+    df = data_sourcing(left_lat, left_lon, dist)
+    if df:
+        st.write("Data loaded successfully !!")
+
+    df = clean_data(df)
+    labelled_df, embeddings_df = autogenerate_labels(df)
+
+    labelled_df.to_csv(f'{data_folder}/DATA_{loc_name}_CLEAN_LABELLED.csv', index=False)
+    embeddings_df.to_csv(f'{data_folder}/DATA_{loc_name}_CLEAN_EMBEDDINGS.csv', index=False)
+
+    st.write("ETL Pipeline executed successfully !!")

src/main.py

@@ -9,11 +9,11 @@ from utilities import get_data, input_filter, clean_data, autogenerate_labels
 
 ################################################## INPUTS ################################################
 
-left_lat = 18.889833
-left_lon = 72.779844
-dist = 35
+# left_lat = 18.889833
+# left_lon = 72.779844
+# dist = 35
 
-def data_sourcing():
+def data_sourcing(left_lat, left_lon, dist):
     lat, lon = input_filter(lat = left_lat, lon=left_lon)
     df = get_data(lat, lon, dist)
     df.to_csv(f'{data_folder}/MMR_DATA.csv', index=False)

utilities/data_loader.py

@@ -168,9 +168,9 @@ def create_map_grid(bottom_left: Tuple[float, float], top_right: Tuple[float, fl
 
 ## entire pipeline
 
-left_lat = 18.889833
-left_lon = 72.779844
-dist = 35
+# left_lat = 18.889833
+# left_lon = 72.779844
+# dist = 35
 
 def input_filter(lat=None, lon=None, string=None):
     if lat != None:
@@ -187,7 +187,7 @@ def get_data(bottom_left_lat, bottom_left_lon, dist):
 
     top_right_lat = result[1][0]
     top_right_lon = result[0][1]
-    grid = create_map_grid((left_lat, left_lon), (top_right_lat, top_right_lon), dist, dist)
+    grid = create_map_grid((bottom_left_lat, bottom_left_lon), (top_right_lat, top_right_lon), dist, dist)
 
     grid_dataset = []
     for i, row in enumerate(grid):