data ingestion + training

app.py

@@ -2,7 +2,67 @@ import streamlit as st
 
 # x = st.slider("Select a value")
 # st.write(x, "squared is", x * x)
+st.title("If you don't have data in your org, enter your API Click the button below! Otherwise, Skep to section 2")
+# -*- coding: utf-8 -*-
+"""
+Original file is located at
+    https://colab.research.google.com/drive/1nOSff67KXhNgX_XSfnv3xnddobRoaK0d
+
+"""
 
+api_key = st.text_input("Enter your api key:", type="password")
+
+import labelbox
+import labelpandas as lp
+import os
+import pandas as pd
+from tensorflow.python.lib.io import file_io
+import io
+from pandas import read_csv
+
+# read csv file from google cloud storage
+def read_data(gcs_path):
+   file_stream = file_io.FileIO(gcs_path, mode='r')
+   csv_data = read_csv(io.StringIO(file_stream.read()))
+   return csv_data
+def freedatatolb(amount_of_data):
+    client = lp.Client(api_key)
+    gcs_path = 'https://storage.googleapis.com/solution_accelerator_datasets/images_styles.csv'
+    df = pd.read_csv(gcs_path)
+    df = df.drop(['id', 'season', 'usage', 'year',"gender", "masterCategory", "subCategory", "articleType","baseColour"], axis =1)
+    fields ={"row_data":["link"], # Column containing URL to asset (single)
+        "global_key": ['filename'], # Column containing globalkey value (single, unique)
+        "external_id": ["productDisplayName"], # Column containing external ID value (single)
+        "metadata_string": [], # Column containing string metadata values (multiple)
+        "metadata_number": [], # Column containing number metadata values (multiple)
+        "metadata_datetime": [] # Column containing datetime metadata values (multiple, must be ISO 8601)
+        }
+    columns = {}
+
+    for field in fields.keys():
+        for name in fields[field]:
+            if field.startswith('metadata'):
+                columns[name] = f"{field.split('_')[0]}///{field.split('_')[1]}///{name}"
+            else:
+                columns[name] = field
+    new_df = df.rename(columns=(columns))
+    testdf = new_df.head(amount_of_data)
+    dataset_id = client.lb_client.create_dataset(name = str(gcs_path.split('/')[-1])).uid
+# dataset_id = client.lb_client.get_dataset("c4b7prd6207850000lljx2hr8").uid
+    results = client.create_data_rows_from_table(
+        table = testdf,
+        dataset_id = dataset_id,
+        skip_duplicates = True, # If True, will skip data rows where a global key is already in use,
+        verbose = True, # If True, prints information about code execution
+    )
+    return results
+data_amount = st.slider("choose amout of data to add to labelbox", 100, 500)
+if st.button("Add data to your Labelbox"):
+    st.write(f"adding {data_amount} datarows to Labelbox instance")
+    bing = freedatatolb(data_amount)
+    st.write(bing)
+             
+st.title("SECTION 2")
 st.title("Auto Image classifier training and inference: Imagnet Weights")
 
 # -*- coding: utf-8 -*-
@@ -284,7 +344,7 @@ def train_and_inference(api_key, ontology_id, model_run_id):
         return prediction_import.errors
 
 st.title("Enter Applicable IDs and keys below")
-api_key = st.text_input("Enter your api key:", type="password")
+
 model_run_id = st.text_input("Enter your model run ID:")
 ontology_id = st.text_input("Enter your ontology ID:")