Fix ModuleNotFoundError on en_core_web_sm

README.md

@@ -300,7 +300,7 @@ git clone https://github.com/microsoft/vcpkg
 | :----------------- | :-------------------------------------------------------------------------------------------------------------------- |
 | **Run Backtest**   | `python -m bbstrader --run backtest --strategy SMAStrategy --account MY_ACCOUNT --config backtest.json`               |
 | **Live Execution** | `python -m bbstrader --run execution --strategy KalmanFilter --account MY_ACCOUNT --config execution.json --parallel` |
-| **Copy Trades**    | `python -m bbstrader --run copier --source 123456 --targets 789012 --risk_multiplier 2.0`                             |
+| **Copy Trades**    | `python -m bbstrader --run copier --source "S1" --destination "D1"`                             |
 | **Get Help**       | `python -m bbstrader --help`                                                                                          |
 
 **Config Example** (`~/.bbstrader/execution/execution.json`):

pyproject.toml

@@ -34,7 +34,6 @@ dependencies = [
     "tweepy>=4.16.0",
     "vaderSentiment>=3.3.2",
     "yfinance>=0.2.65",
-    "en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl",
 ]
 authors = [
     { name = "Bertin Balouki SIMYELI", email = "bertin@bbs-trading.com" },

src/bbstrader/models/nlp.py

@@ -7,19 +7,21 @@
 from typing import Dict, List, Tuple
 
 import dash
-import en_core_web_sm
 import matplotlib.pyplot as plt
 import nltk
 import pandas as pd
 import plotly.express as px
-from bbstrader.core.data import FinancialNews
+import spacy
 from dash import dcc, html
 from dash.dependencies import Input, Output
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
+from spacy.cli import download
 from textblob import TextBlob
 from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
 
+from bbstrader.core.data import FinancialNews
+
 __all__ = [
     "TopicModeler",
     "SentimentAnalyzer",
@@ -349,13 +351,11 @@ def __init__(self):
         nltk.download("stopwords", quiet=True)
 
         try:
-            self.nlp = en_core_web_sm.load()
-            self.nlp.disable_pipes("ner")
+            self.nlp = spacy.load("en_core_web_sm", disable=["ner"])
         except OSError:
-            raise OSError(
-                "SpaCy model 'en_core_web_sm' not found. "
-                "Please install it using 'python -m spacy download en_core_web_sm'."
-            )
+            print("Downloading 'en_core_web_sm' model for spaCy...")
+            download("en_core_web_sm")
+            self.nlp = spacy.load("en_core_web_sm", disable=["ner"])
 
     def preprocess_texts(self, texts: list[str]):
         def clean_doc(Doc):
@@ -403,20 +403,19 @@ def __init__(self):
 
         """
         nltk.download("punkt", quiet=True)
-        nltk.download('punkt_tab', quiet=True)
+        nltk.download("punkt_tab", quiet=True)
         nltk.download("stopwords", quiet=True)
 
         self.analyzer = SentimentIntensityAnalyzer()
         self._stopwords = set(stopwords.words("english"))
 
         try:
-            self.nlp = en_core_web_sm.load()
-            self.nlp.disable_pipes("ner")
+            self.nlp = spacy.load("en_core_web_sm", disable=["ner"])
         except OSError:
-            raise OSError(
-                "SpaCy model 'en_core_web_sm' not found. "
-                "Please install it using 'python -m spacy download en_core_web_sm'."
-            )
+            print("Downloading 'en_core_web_sm' model for spaCy...")
+            download("en_core_web_sm")
+            self.nlp = spacy.load("en_core_web_sm", disable=["ner"])
+
         self.news = FinancialNews()
 
     def preprocess_text(self, text: str):
@@ -930,3 +929,4 @@ def update_dashboard(n):
             return bar_chart, scatter_chart
 
         app.run()
+        app.run()