دسته‌بندی با استفاده از embeddings

 1import pandas as pd
 2import tiktoken
 3
 4# load & inspect dataset
 5input_datapath = "data/fine_food_reviews_1k.csv"  # to save space, we provide a pre-filtered dataset
 6df = pd.read_csv(input_datapath, index_col=0)
 7df = df[["Time", "ProductId", "UserId", "Score", "Summary", "Text"]]
 8df = df.dropna()
 9df["combined"] = (
10    "Title: " + df.Summary.str.strip() + "; Content: " + df.Text.str.strip()
11)
12df.head(2)

 1
 2embedding_model = "text-embedding-3-small"
 3max_tokens = 8000  # the maximum for text-embedding-3-small is 8191
 4embedding_encoding = "cl100k_base"
 5
 6# subsample to 1k most recent reviews and remove samples that are too long
 7top_n = 1000
 8df = df.sort_values("Time").tail(top_n * 2)  # first cut to first 2k entries, assuming less than half will be filtered out
 9df.drop("Time", axis=1, inplace=True)
10
11encoding = tiktoken.get_encoding(embedding_encoding)
12
13# omit reviews that are too long to embed
14df["n_tokens"] = df.combined.apply(lambda x: len(encoding.encode(x)))
15df = df[df.n_tokens <= max_tokens].tail(top_n)

 1
 2from openai import OpenAI # for calling the OpenAI API
 3import os
 4
 5client = OpenAI(
 6    api_key=os.environ.get(("GILAS_API_KEY", "<کلید API خود را اینجا بسازید https://dashboard.gilas.io/apiKey>")), 
 7    base_url="https://api.gilas.io/v1/" # Gilas APIs
 8)
 9
10def get_embedding(query)
11    query_embedding_response = client.embeddings.create(
12        model=embedding_model,
13        input=query,
14    )
15    return query_embedding_response.data[0].embedding
16
17
18# This may take a few minutes
19df["embedding"] = df.combined.apply(lambda x: get_embedding(x))
20df.to_csv("data/fine_food_reviews_with_embeddings_1k.csv")

 1import pandas as pd
 2import numpy as np
 3from ast import literal_eval
 4
 5from sklearn.ensemble import RandomForestClassifier
 6from sklearn.model_selection import train_test_split
 7from sklearn.metrics import classification_report, accuracy_score
 8
 9datafile_path = "data/fine_food_reviews_with_embeddings_1k.csv"
10
11df = pd.read_csv(datafile_path)
12df["embedding"] = df.embedding.apply(literal_eval).apply(np.array)  # convert string to array
13
14# split data into train and test
15X_train, X_test, y_train, y_test = train_test_split(
16    list(df.embedding.values), df.Score, test_size=0.2, random_state=42
17)
18
19# train random forest classifier
20clf = RandomForestClassifier(n_estimators=100)
21clf.fit(X_train, y_train)
22preds = clf.predict(X_test)
23probas = clf.predict_proba(X_test)
24
25report = classification_report(y_test, preds)
26print(report)

1from utils.embeddings_utils import plot_multiclass_precision_recall
2
3plot_multiclass_precision_recall(probas, y_test, [1, 2, 3, 4, 5], clf)