fakedata-python 2.0.1__tar.gz → 2.0.2__tar.gz

{fakedata_python-2.0.1/fakedata_python.egg-info → fakedata_python-2.0.2}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: fakedata-python
-Version: 2.0.1
+Version: 2.0.2
 Summary: The fakedata package generates realistic synthetic user profiles for machine learning, deep learning, data analysis, and data science workflows.
-Author-email: abhay557 <abhaycormourya@gmail.com>
+Author-email: abhay557 <contact@abhaymourya.in>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/abhay557/fakedata
 Classifier: Programming Language :: Python :: 3
@@ -33,8 +33,10 @@ A high-performance, **zero-dependency** synthetic data generation engine, availa
 - **Anomaly Injection**: Inject fraud/outlier profiles (e.g., impossible geography, credit fraud, income spikes) using `anomaly_rate`.
 - **Time-Series Data**: Generate chronological activity logs (logins, page views, purchases) per user for behavioral modeling.
 - **Pipeline Ready**: Export directly to CSV, JSON, or Flat objects (perfect for `pandas.DataFrame`).
+- **CLI Tool**: Generate and export datasets directly from your terminal — no scripting required.
 
 ---
+
 ##  Python Implementation
 
 ### Installation
@@ -58,8 +60,6 @@ print(df.head())
 ts = data.user_time_series({"days": 30, "events_per_day": 8})
 print(f"Generated {len(ts['activity'])} events for {ts['user']['fullName']}")
 ```
-
-
 ##  Node.js / TypeScript Implementation
 
 ### Installation
@@ -81,8 +81,66 @@ const csvString = data.usersToCSV(1000, { seed: 42 });
 const ts = data.userTimeSeries({ days: 30, eventsPerDay: 8 });
 console.log(`Generated ${ts.activity.length} events for ${ts.user.fullName}`);
 ```
+
 ---
 
+##  CLI — Command Line Interface
+
+After installing, use `fakedata` directly from your terminal. No scripts needed!
+
+### Node.js (global install)
+```bash
+npm install -g @abhay557/fakedata
+```
+
+### Python (global install)
+```bash
+pip install fakedata-python
+```
+
+### CLI Commands
+
+| Command | Description |
+|:---|:---|
+| `fakedata generate` | Generate synthetic user data |
+| `fakedata preview` | Print a single user profile to the console |
+| `fakedata help` | Show all available options |
+
+### CLI Options
+
+| Flag | Default | Description |
+|:---|:---|:---|
+| `-n`, `--count` | `10` | Number of users to generate |
+| `-f`, `--format` | `json` | Output format: `json` \| `csv` \| `flat` |
+| `-o`, `--output` | stdout | Output file path |
+| `-s`, `--seed` | none | Random seed for reproducibility |
+| `-l`, `--locale` | `en` | Locale: `en` \| `in` \| `jp` \| `kr` \| `de` \| `br` \| `ar` \| `fr` |
+| `-a`, `--anomaly-rate` | `0` | Fraction of anomalous users (0–1) |
+| `-m`, `--missing-rate` | `0` | Fraction of null fields (0–1) |
+| `-t`, `--timeseries` | — | Include time-series activity logs |
+| `--days` | `30` | Days of activity for time-series |
+| `--pretty` | — | Pretty-print JSON output |
+
+### Examples
+
+```bash
+# Generate 1000 users and save as CSV
+fakedata generate -n 1000 -f csv -o dataset.csv
+
+# Generate 500 deterministic Indian users
+fakedata generate -n 500 -l in --seed 42 -o india.json
+
+# Fraud detection dataset with 5% anomalies
+fakedata generate -n 10000 -a 0.05 -f csv -o fraud_data.csv
+
+# Preview a single user in the console
+fakedata preview
+
+# Time-series activity logs for 100 users
+fakedata generate -n 100 --timeseries --days 60 -o activity.json
+```
+
+---
 ### sample output - one user
 ```fakedata.data.user()``` 
 ```fakedata.data.user(n) // set n = 100```

fakedata_python-2.0.1/PKG-INFO → fakedata_python-2.0.2/README.md

@@ -1,15 +1,3 @@
-Metadata-Version: 2.4
-Name: fakedata-python
-Version: 2.0.1
-Summary: The fakedata package generates realistic synthetic user profiles for machine learning, deep learning, data analysis, and data science workflows.
-Author-email: abhay557 <abhaycormourya@gmail.com>
-License-Expression: MIT
-Project-URL: Homepage, https://github.com/abhay557/fakedata
-Classifier: Programming Language :: Python :: 3
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.7
-Description-Content-Type: text/markdown
-
 # fakedata 
 
 [![NPM Version](https://img.shields.io/npm/v/@abhay557/fakedata?color=red&label=npm)](https://www.npmjs.com/package/@abhay557/fakedata)
@@ -33,8 +21,10 @@ A high-performance, **zero-dependency** synthetic data generation engine, availa
 - **Anomaly Injection**: Inject fraud/outlier profiles (e.g., impossible geography, credit fraud, income spikes) using `anomaly_rate`.
 - **Time-Series Data**: Generate chronological activity logs (logins, page views, purchases) per user for behavioral modeling.
 - **Pipeline Ready**: Export directly to CSV, JSON, or Flat objects (perfect for `pandas.DataFrame`).
+- **CLI Tool**: Generate and export datasets directly from your terminal — no scripting required.
 
 ---
+
 ##  Python Implementation
 
 ### Installation
@@ -58,8 +48,6 @@ print(df.head())
 ts = data.user_time_series({"days": 30, "events_per_day": 8})
 print(f"Generated {len(ts['activity'])} events for {ts['user']['fullName']}")
 ```
-
-
 ##  Node.js / TypeScript Implementation
 
 ### Installation
@@ -81,8 +69,66 @@ const csvString = data.usersToCSV(1000, { seed: 42 });
 const ts = data.userTimeSeries({ days: 30, eventsPerDay: 8 });
 console.log(`Generated ${ts.activity.length} events for ${ts.user.fullName}`);
 ```
+
 ---
 
+##  CLI — Command Line Interface
+
+After installing, use `fakedata` directly from your terminal. No scripts needed!
+
+### Node.js (global install)
+```bash
+npm install -g @abhay557/fakedata
+```
+
+### Python (global install)
+```bash
+pip install fakedata-python
+```
+
+### CLI Commands
+
+| Command | Description |
+|:---|:---|
+| `fakedata generate` | Generate synthetic user data |
+| `fakedata preview` | Print a single user profile to the console |
+| `fakedata help` | Show all available options |
+
+### CLI Options
+
+| Flag | Default | Description |
+|:---|:---|:---|
+| `-n`, `--count` | `10` | Number of users to generate |
+| `-f`, `--format` | `json` | Output format: `json` \| `csv` \| `flat` |
+| `-o`, `--output` | stdout | Output file path |
+| `-s`, `--seed` | none | Random seed for reproducibility |
+| `-l`, `--locale` | `en` | Locale: `en` \| `in` \| `jp` \| `kr` \| `de` \| `br` \| `ar` \| `fr` |
+| `-a`, `--anomaly-rate` | `0` | Fraction of anomalous users (0–1) |
+| `-m`, `--missing-rate` | `0` | Fraction of null fields (0–1) |
+| `-t`, `--timeseries` | — | Include time-series activity logs |
+| `--days` | `30` | Days of activity for time-series |
+| `--pretty` | — | Pretty-print JSON output |
+
+### Examples
+
+```bash
+# Generate 1000 users and save as CSV
+fakedata generate -n 1000 -f csv -o dataset.csv
+
+# Generate 500 deterministic Indian users
+fakedata generate -n 500 -l in --seed 42 -o india.json
+
+# Fraud detection dataset with 5% anomalies
+fakedata generate -n 10000 -a 0.05 -f csv -o fraud_data.csv
+
+# Preview a single user in the console
+fakedata preview
+
+# Time-series activity logs for 100 users
+fakedata generate -n 100 --timeseries --days 60 -o activity.json
+```
+
+---
 ### sample output - one user
 ```fakedata.data.user()``` 
 ```fakedata.data.user(n) // set n = 100```

fakedata_python-2.0.2/fakedata/cli.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+"""
+fakedata CLI - ML-Ready Synthetic Data Engine
+"""
+import argparse
+import json
+import sys
+import time
+import os
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog='fakedata',
+        description='fakedata - ML-Ready Synthetic Data Engine (Python)',
+        formatter_class=argparse.RawTextHelpFormatter,
+        epilog="""
+EXAMPLES:
+  # Generate 1000 users to a CSV file
+  fakedata generate -n 1000 -f csv -o dataset.csv
+
+  # Generate 500 deterministic Indian users
+  fakedata generate -n 500 -l in --seed 42 -o india.json
+
+  # Generate fraud detection dataset with 5%% anomalies
+  fakedata generate -n 10000 -a 0.05 -f csv -o fraud_data.csv
+
+  # Preview a single user profile
+  fakedata preview
+
+  # Generate with time-series activity logs
+  fakedata generate -n 100 --timeseries --days 60 -o activity.json
+        """
+    )
+
+    subparsers = parser.add_subparsers(dest='command', help='Command to run')
+
+    # ─── preview ──────────────────────────────────────────────────────────────
+    subparsers.add_parser('preview', help='Print a single user profile to the console')
+
+    # ─── generate ─────────────────────────────────────────────────────────────
+    gen = subparsers.add_parser('generate', help='Generate synthetic user data')
+    gen.add_argument('-n', '--count', type=int, default=10,
+                     help='Number of users to generate (default: 10)')
+    gen.add_argument('-f', '--format', choices=['json', 'csv', 'flat'], default='json',
+                     help='Output format: json | csv | flat (default: json)')
+    gen.add_argument('-o', '--output', type=str, default=None,
+                     help='Output file path (default: stdout)')
+    gen.add_argument('-s', '--seed', type=int, default=None,
+                     help='Random seed for reproducibility')
+    gen.add_argument('-l', '--locale', type=str, default=None,
+                     help='Locale: en|in|jp|kr|de|br|ar|fr (default: en)')
+    gen.add_argument('-a', '--anomaly-rate', type=float, default=0.0,
+                     help='Fraction of anomalous users 0-1 (default: 0)')
+    gen.add_argument('-m', '--missing-rate', type=float, default=0.0,
+                     help='Fraction of null fields 0-1 (default: 0)')
+    gen.add_argument('-t', '--timeseries', action='store_true',
+                     help='Include time-series activity logs')
+    gen.add_argument('--days', type=int, default=30,
+                     help='Days of activity for time-series (default: 30)')
+    gen.add_argument('--events-per-day', type=int, default=8,
+                     help='Average events per day for time-series (default: 8)')
+    gen.add_argument('--pretty', action='store_true',
+                     help='Pretty-print JSON output')
+
+    args = parser.parse_args()
+
+    if args.command is None or args.command == 'help':
+        parser.print_help()
+        return
+
+    # ─── Import the engine (lazy, only when needed) ───────────────────────────
+    try:
+        import fakedata.modules.data as data
+    except ImportError:
+        print("ERROR: Could not import fakedata. Make sure it is installed: pip install fakedata-python", file=sys.stderr)
+        sys.exit(1)
+
+    # ─── Preview ─────────────────────────────────────────────────────────────
+    if args.command == 'preview':
+        u = data.user()
+        print(json.dumps(u, indent=2))
+        return
+
+    # ─── Generate ────────────────────────────────────────────────────────────
+    if args.command == 'generate':
+        options = {
+            'seed': args.seed,
+            'locale': args.locale,
+            'anomaly_rate': args.anomaly_rate,
+            'missing_rate': args.missing_rate,
+        }
+        # Remove None values so defaults are used inside the engine
+        options = {k: v for k, v in options.items() if v is not None and v != 0.0}
+
+        start = time.time()
+
+        if args.timeseries:
+            results = [
+                data.user_time_series({**options, 'days': args.days, 'events_per_day': args.events_per_day})
+                for _ in range(args.count)
+            ]
+            output = json.dumps(results, indent=2 if args.pretty else None)
+
+        elif args.format == 'csv':
+            output = data.users_to_csv(args.count, options if options else None)
+
+        elif args.format == 'flat':
+            rows = data.users_flat(args.count, options if options else None)
+            output = json.dumps(rows, indent=2 if args.pretty else None)
+
+        else:  # json
+            if args.pretty:
+                output = data.users_to_json(args.count, options if options else None)
+            else:
+                output = json.dumps(data.users(args.count, options if options else None))
+
+        elapsed = round(time.time() - start, 2)
+
+        if args.output:
+            out_path = os.path.abspath(args.output)
+            with open(out_path, 'w', encoding='utf-8') as f:
+                f.write(output)
+            size_kb = round(len(output.encode('utf-8')) / 1024, 1)
+            print(
+                f"✔ Done! Generated {args.count:,} users in {elapsed}s → {out_path} ({size_kb} KB)",
+                file=sys.stderr
+            )
+        else:
+            print(output)
+
+
+if __name__ == '__main__':
+    main()

fakedata_python-2.0.1/README.md → fakedata_python-2.0.2/fakedata_python.egg-info/PKG-INFO

@@ -1,3 +1,15 @@
+Metadata-Version: 2.4
+Name: fakedata-python
+Version: 2.0.2
+Summary: The fakedata package generates realistic synthetic user profiles for machine learning, deep learning, data analysis, and data science workflows.
+Author-email: abhay557 <contact@abhaymourya.in>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/abhay557/fakedata
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+
 # fakedata 
 
 [![NPM Version](https://img.shields.io/npm/v/@abhay557/fakedata?color=red&label=npm)](https://www.npmjs.com/package/@abhay557/fakedata)
@@ -21,8 +33,10 @@ A high-performance, **zero-dependency** synthetic data generation engine, availa
 - **Anomaly Injection**: Inject fraud/outlier profiles (e.g., impossible geography, credit fraud, income spikes) using `anomaly_rate`.
 - **Time-Series Data**: Generate chronological activity logs (logins, page views, purchases) per user for behavioral modeling.
 - **Pipeline Ready**: Export directly to CSV, JSON, or Flat objects (perfect for `pandas.DataFrame`).
+- **CLI Tool**: Generate and export datasets directly from your terminal — no scripting required.
 
 ---
+
 ##  Python Implementation
 
 ### Installation
@@ -46,8 +60,6 @@ print(df.head())
 ts = data.user_time_series({"days": 30, "events_per_day": 8})
 print(f"Generated {len(ts['activity'])} events for {ts['user']['fullName']}")
 ```
-
-
 ##  Node.js / TypeScript Implementation
 
 ### Installation
@@ -69,8 +81,66 @@ const csvString = data.usersToCSV(1000, { seed: 42 });
 const ts = data.userTimeSeries({ days: 30, eventsPerDay: 8 });
 console.log(`Generated ${ts.activity.length} events for ${ts.user.fullName}`);
 ```
+
 ---
 
+##  CLI — Command Line Interface
+
+After installing, use `fakedata` directly from your terminal. No scripts needed!
+
+### Node.js (global install)
+```bash
+npm install -g @abhay557/fakedata
+```
+
+### Python (global install)
+```bash
+pip install fakedata-python
+```
+
+### CLI Commands
+
+| Command | Description |
+|:---|:---|
+| `fakedata generate` | Generate synthetic user data |
+| `fakedata preview` | Print a single user profile to the console |
+| `fakedata help` | Show all available options |
+
+### CLI Options
+
+| Flag | Default | Description |
+|:---|:---|:---|
+| `-n`, `--count` | `10` | Number of users to generate |
+| `-f`, `--format` | `json` | Output format: `json` \| `csv` \| `flat` |
+| `-o`, `--output` | stdout | Output file path |
+| `-s`, `--seed` | none | Random seed for reproducibility |
+| `-l`, `--locale` | `en` | Locale: `en` \| `in` \| `jp` \| `kr` \| `de` \| `br` \| `ar` \| `fr` |
+| `-a`, `--anomaly-rate` | `0` | Fraction of anomalous users (0–1) |
+| `-m`, `--missing-rate` | `0` | Fraction of null fields (0–1) |
+| `-t`, `--timeseries` | — | Include time-series activity logs |
+| `--days` | `30` | Days of activity for time-series |
+| `--pretty` | — | Pretty-print JSON output |
+
+### Examples
+
+```bash
+# Generate 1000 users and save as CSV
+fakedata generate -n 1000 -f csv -o dataset.csv
+
+# Generate 500 deterministic Indian users
+fakedata generate -n 500 -l in --seed 42 -o india.json
+
+# Fraud detection dataset with 5% anomalies
+fakedata generate -n 10000 -a 0.05 -f csv -o fraud_data.csv
+
+# Preview a single user in the console
+fakedata preview
+
+# Time-series activity logs for 100 users
+fakedata generate -n 100 --timeseries --days 60 -o activity.json
+```
+
+---
 ### sample output - one user
 ```fakedata.data.user()``` 
 ```fakedata.data.user(n) // set n = 100```

{fakedata_python-2.0.1 → fakedata_python-2.0.2}/fakedata_python.egg-info/SOURCES.txt

@@ -1,6 +1,7 @@
 README.md
 pyproject.toml
 fakedata/__init__.py
+fakedata/cli.py
 fakedata/core.py
 fakedata/test_python.py
 fakedata/helpers/cardtype.json
@@ -30,4 +31,5 @@ fakedata/modules/data.py
 fakedata_python.egg-info/PKG-INFO
 fakedata_python.egg-info/SOURCES.txt
 fakedata_python.egg-info/dependency_links.txt
+fakedata_python.egg-info/entry_points.txt
 fakedata_python.egg-info/top_level.txt

fakedata_python-2.0.2/fakedata_python.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+fakedata = fakedata.cli:main

{fakedata_python-2.0.1 → fakedata_python-2.0.2}/pyproject.toml

@@ -4,9 +4,9 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fakedata-python"
-version = "2.0.1"
+version = "2.0.2"
 authors = [
-  { name="abhay557", email="abhaycormourya@gmail.com" },
+  { name="abhay557", email="contact@abhaymourya.in" },
 ]
 description = "The fakedata package generates realistic synthetic user profiles for machine learning, deep learning, data analysis, and data science workflows."
 readme = "README.md"
@@ -17,6 +17,9 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 
+[project.scripts]
+fakedata = "fakedata.cli:main"
+
 [project.urls]
 "Homepage" = "https://github.com/abhay557/fakedata"