# Anya's Gojo Revival : Detective Bondman — Data

来源：https://www.kaggle.com/competitions/anyas-gojo-revival-bondman/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

**Data Description for Anya's Gojo Revival: Detective Bondman**

**Files**
- `trainData.csv`: The training dataset with 23 columns, including the 'id' and the 'is_fraud' target column.
- `testData.csv`: The test dataset with 22 columns, missing the 'is_fraud' target column.
- `sample_submission.csv`: A sample submission file in the correct format, including 'id' and predicted 'is_fraud' values.

**Columns**
- `id`: Unique identifier for each entry.
- `trans_date_trans_time`: The date and time of the transaction.
- `cc_num`: Credit card number.
- `merchant`: Merchant receiving payment.
- `category`: Area of merchant's business.
- `amt`: Amount in American Dollars.
- `first`: First name of the cardholder.
- `last`: Last name of the cardholder.
- `gender`: Gender of the cardholder (Male/Female).
- `street`: Street of cardholder's residence.
- `city`: City of cardholder's residence.
- `state`: State of cardholder's residence.
- `zip`: ZIP code of cardholder's residence.
- `lat`: Latitude of the cardholder.
- `long`: Longitude of the cardholder.
- `city_pop`: Population of the city.
- `job`: Occupation of the cardholder.
- `dob`: Date of birth of the cardholder.
- `trans_num`: Transaction ID.
- `unix_time`: Unix time (time since 1970).
- `merch_lat`: Latitude of the merchant.
- `merch_long`: Longitude of the merchant.
- `is_fraud`: Binary flag indicating whether the transaction is fraud (1) or not (0).

**Data Format**
- The datasets are provided in CSV format, with each row representing a data point, and columns containing the feature values.

**Prediction Task**
- Your task is to predict whether each transaction in `testData.csv` is fraudulent (1) or not fraudulent (0) based on patterns and relationships observed in `trainData.csv`.

**Acknowledgments**
- This dataset is fictional and purely for simulation purposes. Any resemblance to real-life cases is coincidental.

Participants should be able to understand the provided data, its format, the task at hand, and the role of each file after reading this data description.