Permalink
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Showing
1 changed file
with
65 additions
and
0 deletions.
There are no files selected for viewing
65
nlp.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,65 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import pandas as pd\n", | ||
"from sklearn.feature_extraction.text import CountVectorizer\n", | ||
"from sklearn.model_selection import train_test_split\n", | ||
"from sklearn.svm import SVC\n", | ||
"from sklearn.metrics import accuracy_score\n", | ||
"\n", | ||
"# Load the data\n", | ||
"df = pd.read_csv('data.csv')\n", | ||
"\n", | ||
"# Preprocess the descriptions by lowercasing and removing punctuation\n", | ||
"df['description'] = df['description'].str.lower()\n", | ||
"df['description'] = df['description'].str.replace(r'[^\\w\\s]', '')\n", | ||
"\n", | ||
"# Split the dataset into training and test sets\n", | ||
"X_train, X_test, y_train, y_test = train_test_split(df['description'], df['timeS'], test_size=0.2)\n", | ||
"\n", | ||
"# Extract features using a bag-of-words approach\n", | ||
"vectorizer = CountVectorizer()\n", | ||
"X_train_features = vectorizer.fit_transform(X_train)\n", | ||
"X_test_features = vectorizer.transform(X_test)\n", | ||
"\n", | ||
"# Train a support vector machine classifier\n", | ||
"classifier = SVC()\n", | ||
"output = classifier.fit(X_train_features, y_train)\n", | ||
"output.save('model.m5')\n", | ||
"\n", | ||
"# Make predictions on the test set\n", | ||
"y_pred = classifier.predict(X_test_features)\n", | ||
"\n", | ||
"# Evaluate the model's performance\n", | ||
"accuracy = accuracy_score(y_test, y_pred)\n", | ||
"print(f'Model accuracy: {accuracy:.2f}')" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "Python (Pyodide)", | ||
"language": "python", | ||
"name": "python" | ||
}, | ||
"language_info": { | ||
"codemirror_mode": { | ||
"name": "python", | ||
"version": 3 | ||
}, | ||
"file_extension": ".py", | ||
"mimetype": "text/x-python", | ||
"name": "python", | ||
"nbconvert_exporter": "python", | ||
"pygments_lexer": "ipython3", | ||
"version": "3.8" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 4 | ||
} |