{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":35628,"databundleVersionId":3418154}],"dockerImageVersionId":31286,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-03-09T10:59:46.721179Z","iopub.execute_input":"2026-03-09T10:59:46.721467Z","iopub.status.idle":"2026-03-09T10:59:48.032260Z","shell.execute_reply.started":"2026-03-09T10:59:46.721440Z","shell.execute_reply":"2026-03-09T10:59:48.031293Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"![image.png](attachment:d3ea220c-01ea-442d-a26a-0868c631c9f3.png)","metadata":{},"attachments":{"d3ea220c-01ea-442d-a26a-0868c631c9f3.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Business Goal\nThe goal of this project is to predict a target outcome from fashion and beauty related reviews or product-related data.\nThis target is usually a class label, score, satisfaction level, or a similar output variable.\n\nBusiness value:\n\npredicting customer satisfaction,\n\nmeasuring product perception,\n\ngenerating automated decision support from reviews,\n\nhelping brands analyze product performance faster.","metadata":{}},{"cell_type":"markdown","source":"# Target","metadata":{}},{"cell_type":"markdown","source":"The target is the column the model is trying to predict.\nWe will not guess it. We will detect it from the dataset.\n\nPractical rule:\n\nit exists in train,\n\nit does not exist in test,\n\nit is the value required in the submission file.","metadata":{}},{"cell_type":"markdown","source":"# Import Libraries","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:04:24.037833Z","iopub.execute_input":"2026-03-09T11:04:24.038844Z","iopub.status.idle":"2026-03-09T11:04:24.044240Z","shell.execute_reply.started":"2026-03-09T11:04:24.038806Z","shell.execute_reply":"2026-03-09T11:04:24.043185Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Read Dataset","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/competitions/fashion-and-beauty-reviews/review_train.tsv\", sep=\"\\t\")\ntest = pd.read_csv(\"/kaggle/input/competitions/fashion-and-beauty-reviews/review_test_post.tsv\", sep=\"\\t\")\nsample_sub = pd.read_csv(\"/kaggle/input/competitions/fashion-and-beauty-reviews/sample_submission.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:06:06.787802Z","iopub.execute_input":"2026-03-09T11:06:06.788786Z","iopub.status.idle":"2026-03-09T11:06:21.667919Z","shell.execute_reply.started":"2026-03-09T11:06:06.788745Z","shell.execute_reply":"2026-03-09T11:06:21.666911Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:06:29.240856Z","iopub.execute_input":"2026-03-09T11:06:29.241249Z","iopub.status.idle":"2026-03-09T11:06:29.279534Z","shell.execute_reply.started":"2026-03-09T11:06:29.241216Z","shell.execute_reply":"2026-03-09T11:06:29.278498Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:06:35.412526Z","iopub.execute_input":"2026-03-09T11:06:35.412921Z","iopub.status.idle":"2026-03-09T11:06:35.422867Z","shell.execute_reply.started":"2026-03-09T11:06:35.412889Z","shell.execute_reply":"2026-03-09T11:06:35.422026Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample_sub.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:06:40.169562Z","iopub.execute_input":"2026-03-09T11:06:40.169894Z","iopub.status.idle":"2026-03-09T11:06:40.178921Z","shell.execute_reply.started":"2026-03-09T11:06:40.169865Z","shell.execute_reply":"2026-03-09T11:06:40.177839Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# EDA","metadata":{}},{"cell_type":"code","source":"train.shape, test.shape, sample_sub.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:06:52.009782Z","iopub.execute_input":"2026-03-09T11:06:52.010336Z","iopub.status.idle":"2026-03-09T11:06:52.016434Z","shell.execute_reply.started":"2026-03-09T11:06:52.010303Z","shell.execute_reply":"2026-03-09T11:06:52.015566Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.columns ,test.columns ,sample_sub.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:07:19.844902Z","iopub.execute_input":"2026-03-09T11:07:19.846121Z","iopub.status.idle":"2026-03-09T11:07:19.852691Z","shell.execute_reply.started":"2026-03-09T11:07:19.846078Z","shell.execute_reply":"2026-03-09T11:07:19.851735Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:07:56.180584Z","iopub.execute_input":"2026-03-09T11:07:56.180955Z","iopub.status.idle":"2026-03-09T11:07:56.429818Z","shell.execute_reply.started":"2026-03-09T11:07:56.180908Z","shell.execute_reply":"2026-03-09T11:07:56.428656Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:08:03.448389Z","iopub.execute_input":"2026-03-09T11:08:03.448712Z","iopub.status.idle":"2026-03-09T11:08:03.516191Z","shell.execute_reply.started":"2026-03-09T11:08:03.448683Z","shell.execute_reply":"2026-03-09T11:08:03.514960Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.isnull().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:08:21.645426Z","iopub.execute_input":"2026-03-09T11:08:21.645748Z","iopub.status.idle":"2026-03-09T11:08:21.882881Z","shell.execute_reply.started":"2026-03-09T11:08:21.645722Z","shell.execute_reply":"2026-03-09T11:08:21.881810Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.isnull().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:08:27.482561Z","iopub.execute_input":"2026-03-09T11:08:27.482878Z","iopub.status.idle":"2026-03-09T11:08:27.548672Z","shell.execute_reply.started":"2026-03-09T11:08:27.482852Z","shell.execute_reply":"2026-03-09T11:08:27.547697Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.nunique()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:09:02.662549Z","iopub.execute_input":"2026-03-09T11:09:02.662974Z","iopub.status.idle":"2026-03-09T11:09:03.806376Z","shell.execute_reply.started":"2026-03-09T11:09:02.662913Z","shell.execute_reply":"2026-03-09T11:09:03.805359Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train[\"rating\"].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:11:29.064063Z","iopub.execute_input":"2026-03-09T11:11:29.065225Z","iopub.status.idle":"2026-03-09T11:11:29.087573Z","shell.execute_reply.started":"2026-03-09T11:11:29.065185Z","shell.execute_reply":"2026-03-09T11:11:29.086769Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Feature Engineering","metadata":{}},{"cell_type":"code","source":"train[\"review\"] = train[\"review\"].fillna(\"\")\ntrain[\"summary\"] = train[\"summary\"].fillna(\"\")\ntest[\"review\"] = test[\"review\"].fillna(\"\")\ntest[\"summary\"] = test[\"summary\"].fillna(\"\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:16:46.323912Z","iopub.execute_input":"2026-03-09T11:16:46.324312Z","iopub.status.idle":"2026-03-09T11:16:46.621455Z","shell.execute_reply.started":"2026-03-09T11:16:46.324282Z","shell.execute_reply":"2026-03-09T11:16:46.620268Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train[\"text\"] = train[\"review\"] + \" \" + train[\"summary\"]\ntest[\"text\"] = test[\"review\"] + \" \" + test[\"summary\"]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:16:58.032427Z","iopub.execute_input":"2026-03-09T11:16:58.032797Z","iopub.status.idle":"2026-03-09T11:16:58.721704Z","shell.execute_reply.started":"2026-03-09T11:16:58.032765Z","shell.execute_reply":"2026-03-09T11:16:58.720915Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train[[\"rating\", \"text\"]].head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:17:13.122214Z","iopub.execute_input":"2026-03-09T11:17:13.122718Z","iopub.status.idle":"2026-03-09T11:17:13.163155Z","shell.execute_reply.started":"2026-03-09T11:17:13.122676Z","shell.execute_reply":"2026-03-09T11:17:13.162217Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# X/Y split","metadata":{}},{"cell_type":"code","source":"x = train[\"text\"]\ny = train[\"rating\"]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:17:59.924799Z","iopub.execute_input":"2026-03-09T11:17:59.925161Z","iopub.status.idle":"2026-03-09T11:17:59.930333Z","shell.execute_reply.started":"2026-03-09T11:17:59.925132Z","shell.execute_reply":"2026-03-09T11:17:59.929322Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"x.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:18:12.085036Z","iopub.execute_input":"2026-03-09T11:18:12.085572Z","iopub.status.idle":"2026-03-09T11:18:12.092414Z","shell.execute_reply.started":"2026-03-09T11:18:12.085530Z","shell.execute_reply":"2026-03-09T11:18:12.091439Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:18:17.091527Z","iopub.execute_input":"2026-03-09T11:18:17.091852Z","iopub.status.idle":"2026-03-09T11:18:17.099512Z","shell.execute_reply.started":"2026-03-09T11:18:17.091825Z","shell.execute_reply":"2026-03-09T11:18:17.098546Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nx_train, x_valid, y_train, y_valid = train_test_split( x,y,test_size=0.2,random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:20:01.896750Z","iopub.execute_input":"2026-03-09T11:20:01.897124Z","iopub.status.idle":"2026-03-09T11:20:03.005091Z","shell.execute_reply.started":"2026-03-09T11:20:01.897095Z","shell.execute_reply":"2026-03-09T11:20:03.003954Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"80% of the data is used for training and 20% for validation.","metadata":{}},{"cell_type":"markdown","source":"# TF-IDF Vectorization","metadata":{}},{"cell_type":"code","source":"from sklearn.feature_extraction.text import TfidfVectorizer\n\nvectorizer = TfidfVectorizer(max_features=30000,ngram_range=(1,2),stop_words=\"english\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:20:54.998426Z","iopub.execute_input":"2026-03-09T11:20:54.998876Z","iopub.status.idle":"2026-03-09T11:20:55.019066Z","shell.execute_reply.started":"2026-03-09T11:20:54.998848Z","shell.execute_reply":"2026-03-09T11:20:55.017897Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"x_train_vec = vectorizer.fit_transform(x_train)\nx_valid_vec = vectorizer.transform(x_valid)\nx_test_vec = vectorizer.transform(test[\"text\"])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:21:17.656982Z","iopub.execute_input":"2026-03-09T11:21:17.658066Z","iopub.status.idle":"2026-03-09T11:22:29.586191Z","shell.execute_reply.started":"2026-03-09T11:21:17.658024Z","shell.execute_reply":"2026-03-09T11:22:29.585221Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Text is converted into a sparse numerical matrix.","metadata":{}},{"cell_type":"markdown","source":"# Modelling","metadata":{}},{"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\n\nmodel = LogisticRegression(max_iter=300)\n\nmodel.fit(x_train_vec, y_train)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:22:34.380067Z","iopub.execute_input":"2026-03-09T11:22:34.380399Z","iopub.status.idle":"2026-03-09T11:25:15.998056Z","shell.execute_reply.started":"2026-03-09T11:22:34.380371Z","shell.execute_reply":"2026-03-09T11:25:15.997033Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\n\npred_valid = model.predict(x_valid_vec)\n\naccuracy_score(y_valid, pred_valid)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:25:30.376708Z","iopub.execute_input":"2026-03-09T11:25:30.377233Z","iopub.status.idle":"2026-03-09T11:25:30.427204Z","shell.execute_reply.started":"2026-03-09T11:25:30.377199Z","shell.execute_reply":"2026-03-09T11:25:30.426247Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_pred = model.predict(x_test_vec)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:25:32.575173Z","iopub.execute_input":"2026-03-09T11:25:32.575531Z","iopub.status.idle":"2026-03-09T11:25:32.628983Z","shell.execute_reply.started":"2026-03-09T11:25:32.575502Z","shell.execute_reply":"2026-03-09T11:25:32.627996Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample_sub = pd.read_csv(\"/kaggle/input/competitions/fashion-and-beauty-reviews/sample_submission.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:27:42.309392Z","iopub.execute_input":"2026-03-09T11:27:42.309748Z","iopub.status.idle":"2026-03-09T11:27:42.325132Z","shell.execute_reply.started":"2026-03-09T11:27:42.309720Z","shell.execute_reply":"2026-03-09T11:27:42.324223Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample_sub.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:27:53.534756Z","iopub.execute_input":"2026-03-09T11:27:53.535130Z","iopub.status.idle":"2026-03-09T11:27:53.544197Z","shell.execute_reply.started":"2026-03-09T11:27:53.535099Z","shell.execute_reply":"2026-03-09T11:27:53.543123Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample_sub.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:27:59.001667Z","iopub.execute_input":"2026-03-09T11:27:59.002230Z","iopub.status.idle":"2026-03-09T11:27:59.008436Z","shell.execute_reply.started":"2026-03-09T11:27:59.002190Z","shell.execute_reply":"2026-03-09T11:27:59.007573Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"id\": range(1, len(test_pred) + 1),\n    \"rating\": test_pred\n})","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:29:05.332424Z","iopub.execute_input":"2026-03-09T11:29:05.333319Z","iopub.status.idle":"2026-03-09T11:29:05.338905Z","shell.execute_reply.started":"2026-03-09T11:29:05.333270Z","shell.execute_reply":"2026-03-09T11:29:05.338011Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission.to_csv(\"submission.csv\", index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:29:14.850138Z","iopub.execute_input":"2026-03-09T11:29:14.851443Z","iopub.status.idle":"2026-03-09T11:29:15.165791Z","shell.execute_reply.started":"2026-03-09T11:29:14.851397Z","shell.execute_reply":"2026-03-09T11:29:15.164969Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\nsubmission.head(), submission.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:30:25.217891Z","iopub.execute_input":"2026-03-09T11:30:25.218279Z","iopub.status.idle":"2026-03-09T11:30:25.226910Z","shell.execute_reply.started":"2026-03-09T11:30:25.218248Z","shell.execute_reply":"2026-03-09T11:30:25.225802Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import joblib\n\njoblib.dump(model, \"beauty_review_model.pkl\")\njoblib.dump(vectorizer, \"tfidf_vectorizer.pkl\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:29:26.965976Z","iopub.execute_input":"2026-03-09T11:29:26.966822Z","iopub.status.idle":"2026-03-09T11:29:27.548845Z","shell.execute_reply.started":"2026-03-09T11:29:26.966788Z","shell.execute_reply":"2026-03-09T11:29:27.547762Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Conclusion","metadata":{}},{"cell_type":"markdown","source":"In this project, a machine learning pipeline was developed to predict product ratings based on customer reviews in the fashion and beauty domain. The dataset contains textual information such as review content and review summaries, along with product and reviewer identifiers.\n\nThe main goal was to build a baseline natural language processing model capable of learning sentiment and contextual information from user reviews in order to predict rating scores ranging from 1 to 5.\n\nTo achieve this, the following workflow was implemented:\n\nData preprocessing and missing value handling were applied to ensure clean textual inputs.\n\nReview text and summary fields were combined into a single text feature to provide richer contextual information.\n\nThe dataset was split into training and validation sets to evaluate model performance.\n\nText data was transformed into numerical representations using TF-IDF vectorization with unigram and bigram features.\n\nA Logistic Regression classifier was trained on the vectorized text features.\n\nModel performance was evaluated using validation accuracy.\n\nThe baseline model achieved an accuracy of approximately 0.71 on the validation set, demonstrating that textual customer feedback contains strong predictive signals for product ratings.\n\nThis result indicates that even a relatively simple machine learning pipeline can effectively capture sentiment patterns within customer reviews.\n\nFuture improvements could include:\n\nexperimenting with more advanced models such as Linear SVM or gradient boosting classifiers,\n\nusing larger n-gram ranges or character-level features,\n\napplying deep learning or transformer-based NLP models for richer semantic understanding.\n\nOverall, this project demonstrates how classical NLP techniques combined with lightweight machine learning models can produce competitive results for large-scale text classification problems.","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}