ready

app.py

@@ -2,6 +2,11 @@ from fastapi import FastAPI
 from dotenv import load_dotenv
 from tasks import text, image, audio
 
+from skops.hub_utils import download
+
+#download model for text task
+download(repo_id = "kantundpeterpan/frugal-ai-toy", dst = "text/model")
+
 # Load environment variables
 load_dotenv()
 

tasks/text.py

@@ -15,25 +15,10 @@ import joblib
 REPO_ID = "kantundpeterpan/frugal-ai-toy"
 FILENAME = "tfidf_rf.skops"
 
-# import nltk
-# from nltk.tokenize import WordPunctTokenizer
-# from nltk.stem import WordNetLemmatizer
-# from nltk.corpus import stopwords
-# import string
-# nltk.download('stopwords')
-
-# stop = set(stopwords.words('english') + list(string.punctuation))
-
-# def tokenize_quote(r):
-#     tokens = nltk.word_tokenize(r.lower())
-#     cleaned = [word for word in tokens if word not in stop]
-#     return cleaned
-
-# def lemmatize_tokens(tokens: list):
-#     return [lemmatizer.lemmatize(t) for t in tokens]
-
-# def lemmatize_X(X):
-#     return X.quote.apply(tokenize_quote).apply(lemmatize_tokens).apply(lambda x: " ".join(x))
+#add model directory to python path to be able to load tools.py
+import sys
+import os
+sys.path.append(os.path.abspath('model'))
 
 import random
 
@@ -80,6 +65,7 @@ async def evaluate_text(request: TextEvaluationRequest):
     train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
     test_dataset = train_test["test"]
     test_df = pd.DataFrame(test_dataset)
+    print(test_df.head())
     
     # Start tracking emissions
     tracker.start()
@@ -90,14 +76,11 @@ async def evaluate_text(request: TextEvaluationRequest):
     # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
     #--------------------------------------------------------------------------------------------   
 
-    
-    #download model
-    download(repo_id = "kantundpeterpan/frugal-ai-toy", dst = "skops_test")
     #get unknwown types
-    unknown = skops.io.get_untrusted_types(file = "skops_test/tfidf_rf.skops")
+    unknown = skops.io.get_untrusted_types(file = "model/tfidf_rf.skops")
     
     #load model
-    model = model = load("skops_test/tfidf_rf.skops", trusted = unknown)
+    model = model = load("model/tfidf_rf.skops", trusted = unknown)
     
     # Make predictions
     true_labels = test_dataset["label"]