seaborn-lite 0.1.0__tar.gz

seaborn_lite-0.1.0/PKG-INFO

@@ -0,0 +1,159 @@
+Metadata-Version: 2.4
+Name: seaborn-lite
+Version: 0.1.0
+Summary: A tiny matplotlib-only seaborn subset plus the DWM practical-exam algorithms, from scratch.
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: matplotlib>=3.7
+
+# seaborn-lite
+
+A tiny, matplotlib-only subset of seaborn **plus** every algorithm from the
+DWM practical exam and every experiment write-up, packaged for direct use.
+
+No seaborn, no scikit-learn, no scipy — just `numpy`, `pandas` and `matplotlib`.
+
+## Install
+
+```bash
+pip install .
+```
+
+That installs the distribution `seaborn-lite` and the import package
+`seaborn_lite`, bundles the 14 exam datasets, and adds the `seaborn-lite`
+command. To publish it so `pip install seaborn-lite` works from anywhere, build
+and upload it with `python -m build` + `twine upload dist/*`.
+
+## Print an experiment write-up
+
+Every experiment `.txt` is bundled. One function per experiment prints it
+verbatim and returns the same text:
+
+```python
+import seaborn_lite as snsl
+
+snsl.apriori()      # prints 05_APRIORI_FREQUENT_PATTERNS.txt
+snsl.sql()          # prints 01_SQL_EXPERIMENTS.txt
+snsl.list()         # shows every available function
+```
+
+| Function | Prints |
+| :--- | :--- |
+| `sql()` | `01_SQL_EXPERIMENTS.txt` |
+| `star_schema()` | `02_STAR_SCHEMA_AND_15_QUERIES.txt` |
+| `olap()` | `03_OLAP_OPERATIONS.txt` |
+| `preprocessing()`, `data_preprocessing()` | `04_DATA_PREPROCESSING_AND_VISUALISATION.txt` |
+| `apriori()`, `appriori()` | `05_APRIORI_FREQUENT_PATTERNS.txt` |
+| `kmeans()`, `kmedoids()` | `06_KMEANS_AND_KMEDOIDS.txt` |
+| `hierarchical()`, `hierarchical_clustering()` | `07_HIERARCHICAL_CLUSTERING.txt` |
+| `naive_bayes()`, `categorical_naive_bayes()`, `gaussian_naive_bayes()` | `08_NAIVE_BAYES.txt` |
+| `pagerank()`, `hits()` | `09_PAGERANK_AND_HITS.txt` |
+| `all_experiments()` | `DWM_ALL_EXPERIMENTS_ONE_FILE.txt` |
+
+`snsl.list()` prints this table with the exact function names and file names.
+The algorithm implementations live under `seaborn_lite.dwm`, so
+`snsl.kmeans()` prints the write-up while `seaborn_lite.dwm.kmeans(X, k=3)`
+does the clustering.
+
+## Plotting
+
+```python
+import seaborn_lite as sns
+from seaborn_lite import datasets
+
+df = datasets.load("customer_churn_raw")
+sns.set_theme()
+sns.histplot(df, x="Age", kde=True)
+sns.countplot(df, x="Contract_Type")
+sns.heatmap(df.select_dtypes("number").corr(), annot=True)
+```
+
+Supported: `histplot`, `countplot`, `barplot`, `boxplot`, `scatterplot`,
+`heatmap`, `pairplot`, `set_theme`. Same `data=` / `x=` / `y=` calling style as
+seaborn; each returns the matplotlib `Axes` (except `pairplot`, which returns an
+object with `.fig` and `.savefig`).
+
+## Algorithms
+
+```python
+from seaborn_lite import datasets
+from seaborn_lite.dwm import kmeans
+from seaborn_lite.dwm.itemsets import apriori, transactions_from_dataframe
+
+X = datasets.load("mall_customers").select_dtypes("number").to_numpy()
+result = kmeans(X, k=3)
+print(result.centroids, result.wcss)
+
+tx = transactions_from_dataframe(datasets.load("transactions_list"))
+frequent = apriori(tx, min_support=0.3)
+```
+
+### API by experiment
+
+| Experiment | Import | Main callables |
+| :--- | :--- | :--- |
+| 3 · OLAP | `from seaborn_lite.dwm import olap` | `rollup`, `drilldown`, `slice_cube`, `dice_cube`, `pivot` |
+| 4 · Explore | `from seaborn_lite.dwm import explore` | `explore(df) -> dict` |
+| 4 · Clean | `from seaborn_lite.dwm import clean_dataframe` | `clean_dataframe(df, rename=...)` |
+| 4 · Preprocess | `from seaborn_lite.dwm import preprocessing` | `discretize`, `label_encode`, `one_hot_encode`, `minmax_scale`, `zscore_scale`, `train_test_split` |
+| 4 · Visualise | `from seaborn_lite.dwm import plot_all` | `plot_all(df, out_dir)` |
+| 4 · Pivot | `from seaborn_lite.dwm import grouping` | `group_summary`, `multi_agg`, `pivot_table` |
+| 5 · Apriori | `from seaborn_lite.dwm import apriori, association_rules` | `apriori(transactions, min_support)`, `association_rules(frequent, transactions, min_confidence)` |
+| 6 · K-Means | `from seaborn_lite.dwm import kmeans, elbow` | `kmeans(X, k) -> KMeansResult`, `elbow(X, k_max)` |
+| 6 · K-Medoids | `from seaborn_lite.dwm import kmedoids` | `kmedoids(X, k) -> KMedoidsResult` |
+| 7 · Hierarchical | `from seaborn_lite.dwm import agglomerative, silhouette_score, plot_dendrogram` | four linkages (`single`/`complete`/`average`/`ward`), `scale=True` for StandardScaler behaviour |
+| 8 · Naive Bayes | `from seaborn_lite.dwm import CategoricalNB, GaussianNB` | scikit-learn-shaped `fit` / `predict` / `predict_proba` |
+| 9 · PageRank | `from seaborn_lite.dwm import pagerank, hits` | `pagerank(graph) -> dict`, `hits(graph) -> (hubs, authorities)` |
+
+## Datasets
+
+```python
+from seaborn_lite import datasets
+
+datasets.available()          # 14 names
+datasets.load("play_tennis")  # DataFrame
+datasets.path("play_tennis")  # Path to the bundled CSV
+```
+
+## CLI
+
+```bash
+seaborn-lite list
+seaborn-lite datasets
+seaborn-lite run kmeans
+seaborn-lite run visualise --out ./plots
+seaborn-lite run apriori --data my_baskets.csv
+```
+
+Demos: `apriori`, `kmeans`, `kmedoids`, `hierarchical`, `nb-categorical`,
+`nb-gaussian`, `pagerank`, `hits`, `olap`, `explore`, `clean`, `preprocess`,
+`pivot`, `visualise`.
+
+## Layout
+
+```text
+seaborn-lite/
+├── seaborn_lite/
+│   ├── plotting.py        # the seaborn subset
+│   ├── experiments/       # the 10 bundled .txt write-ups + printers/list()
+│   ├── datasets/          # bundled CSVs + loaders
+│   ├── demos.py           # what the CLI runs
+│   ├── cli.py
+│   └── dwm/               # the exam algorithms
+├── tests/selfcheck.py     # assert-based, no test framework
+├── pyproject.toml
+└── DWM_PRACTICAL_EXAM/    # original exam submission, left untouched
+```
+
+## Verify
+
+```bash
+python tests/selfcheck.py
+```
+
+This loads every dataset, checks known results (17 Apriori itemsets, Ward
+silhouette 0.2352, 13/14 Tennis accuracy, PageRank ranking), writes all eight
+plots, and runs every CLI demo.

seaborn_lite-0.1.0/README.md

@@ -0,0 +1,148 @@
+# seaborn-lite
+
+A tiny, matplotlib-only subset of seaborn **plus** every algorithm from the
+DWM practical exam and every experiment write-up, packaged for direct use.
+
+No seaborn, no scikit-learn, no scipy — just `numpy`, `pandas` and `matplotlib`.
+
+## Install
+
+```bash
+pip install .
+```
+
+That installs the distribution `seaborn-lite` and the import package
+`seaborn_lite`, bundles the 14 exam datasets, and adds the `seaborn-lite`
+command. To publish it so `pip install seaborn-lite` works from anywhere, build
+and upload it with `python -m build` + `twine upload dist/*`.
+
+## Print an experiment write-up
+
+Every experiment `.txt` is bundled. One function per experiment prints it
+verbatim and returns the same text:
+
+```python
+import seaborn_lite as snsl
+
+snsl.apriori()      # prints 05_APRIORI_FREQUENT_PATTERNS.txt
+snsl.sql()          # prints 01_SQL_EXPERIMENTS.txt
+snsl.list()         # shows every available function
+```
+
+| Function | Prints |
+| :--- | :--- |
+| `sql()` | `01_SQL_EXPERIMENTS.txt` |
+| `star_schema()` | `02_STAR_SCHEMA_AND_15_QUERIES.txt` |
+| `olap()` | `03_OLAP_OPERATIONS.txt` |
+| `preprocessing()`, `data_preprocessing()` | `04_DATA_PREPROCESSING_AND_VISUALISATION.txt` |
+| `apriori()`, `appriori()` | `05_APRIORI_FREQUENT_PATTERNS.txt` |
+| `kmeans()`, `kmedoids()` | `06_KMEANS_AND_KMEDOIDS.txt` |
+| `hierarchical()`, `hierarchical_clustering()` | `07_HIERARCHICAL_CLUSTERING.txt` |
+| `naive_bayes()`, `categorical_naive_bayes()`, `gaussian_naive_bayes()` | `08_NAIVE_BAYES.txt` |
+| `pagerank()`, `hits()` | `09_PAGERANK_AND_HITS.txt` |
+| `all_experiments()` | `DWM_ALL_EXPERIMENTS_ONE_FILE.txt` |
+
+`snsl.list()` prints this table with the exact function names and file names.
+The algorithm implementations live under `seaborn_lite.dwm`, so
+`snsl.kmeans()` prints the write-up while `seaborn_lite.dwm.kmeans(X, k=3)`
+does the clustering.
+
+## Plotting
+
+```python
+import seaborn_lite as sns
+from seaborn_lite import datasets
+
+df = datasets.load("customer_churn_raw")
+sns.set_theme()
+sns.histplot(df, x="Age", kde=True)
+sns.countplot(df, x="Contract_Type")
+sns.heatmap(df.select_dtypes("number").corr(), annot=True)
+```
+
+Supported: `histplot`, `countplot`, `barplot`, `boxplot`, `scatterplot`,
+`heatmap`, `pairplot`, `set_theme`. Same `data=` / `x=` / `y=` calling style as
+seaborn; each returns the matplotlib `Axes` (except `pairplot`, which returns an
+object with `.fig` and `.savefig`).
+
+## Algorithms
+
+```python
+from seaborn_lite import datasets
+from seaborn_lite.dwm import kmeans
+from seaborn_lite.dwm.itemsets import apriori, transactions_from_dataframe
+
+X = datasets.load("mall_customers").select_dtypes("number").to_numpy()
+result = kmeans(X, k=3)
+print(result.centroids, result.wcss)
+
+tx = transactions_from_dataframe(datasets.load("transactions_list"))
+frequent = apriori(tx, min_support=0.3)
+```
+
+### API by experiment
+
+| Experiment | Import | Main callables |
+| :--- | :--- | :--- |
+| 3 · OLAP | `from seaborn_lite.dwm import olap` | `rollup`, `drilldown`, `slice_cube`, `dice_cube`, `pivot` |
+| 4 · Explore | `from seaborn_lite.dwm import explore` | `explore(df) -> dict` |
+| 4 · Clean | `from seaborn_lite.dwm import clean_dataframe` | `clean_dataframe(df, rename=...)` |
+| 4 · Preprocess | `from seaborn_lite.dwm import preprocessing` | `discretize`, `label_encode`, `one_hot_encode`, `minmax_scale`, `zscore_scale`, `train_test_split` |
+| 4 · Visualise | `from seaborn_lite.dwm import plot_all` | `plot_all(df, out_dir)` |
+| 4 · Pivot | `from seaborn_lite.dwm import grouping` | `group_summary`, `multi_agg`, `pivot_table` |
+| 5 · Apriori | `from seaborn_lite.dwm import apriori, association_rules` | `apriori(transactions, min_support)`, `association_rules(frequent, transactions, min_confidence)` |
+| 6 · K-Means | `from seaborn_lite.dwm import kmeans, elbow` | `kmeans(X, k) -> KMeansResult`, `elbow(X, k_max)` |
+| 6 · K-Medoids | `from seaborn_lite.dwm import kmedoids` | `kmedoids(X, k) -> KMedoidsResult` |
+| 7 · Hierarchical | `from seaborn_lite.dwm import agglomerative, silhouette_score, plot_dendrogram` | four linkages (`single`/`complete`/`average`/`ward`), `scale=True` for StandardScaler behaviour |
+| 8 · Naive Bayes | `from seaborn_lite.dwm import CategoricalNB, GaussianNB` | scikit-learn-shaped `fit` / `predict` / `predict_proba` |
+| 9 · PageRank | `from seaborn_lite.dwm import pagerank, hits` | `pagerank(graph) -> dict`, `hits(graph) -> (hubs, authorities)` |
+
+## Datasets
+
+```python
+from seaborn_lite import datasets
+
+datasets.available()          # 14 names
+datasets.load("play_tennis")  # DataFrame
+datasets.path("play_tennis")  # Path to the bundled CSV
+```
+
+## CLI
+
+```bash
+seaborn-lite list
+seaborn-lite datasets
+seaborn-lite run kmeans
+seaborn-lite run visualise --out ./plots
+seaborn-lite run apriori --data my_baskets.csv
+```
+
+Demos: `apriori`, `kmeans`, `kmedoids`, `hierarchical`, `nb-categorical`,
+`nb-gaussian`, `pagerank`, `hits`, `olap`, `explore`, `clean`, `preprocess`,
+`pivot`, `visualise`.
+
+## Layout
+
+```text
+seaborn-lite/
+├── seaborn_lite/
+│   ├── plotting.py        # the seaborn subset
+│   ├── experiments/       # the 10 bundled .txt write-ups + printers/list()
+│   ├── datasets/          # bundled CSVs + loaders
+│   ├── demos.py           # what the CLI runs
+│   ├── cli.py
+│   └── dwm/               # the exam algorithms
+├── tests/selfcheck.py     # assert-based, no test framework
+├── pyproject.toml
+└── DWM_PRACTICAL_EXAM/    # original exam submission, left untouched
+```
+
+## Verify
+
+```bash
+python tests/selfcheck.py
+```
+
+This loads every dataset, checks known results (17 Apriori itemsets, Ward
+silhouette 0.2352, 13/14 Tennis accuracy, PageRank ranking), writes all eight
+plots, and runs every CLI demo.

seaborn_lite-0.1.0/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "seaborn-lite"
+version = "0.1.0"
+description = "A tiny matplotlib-only seaborn subset plus the DWM practical-exam algorithms, from scratch."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+dependencies = [
+    "numpy>=1.24",
+    "pandas>=2.0",
+    "matplotlib>=3.7",
+]
+
+[project.scripts]
+seaborn-lite = "seaborn_lite.cli:main"
+
+[tool.setuptools.packages.find]
+include = ["seaborn_lite*"]
+
+[tool.setuptools.package-data]
+"seaborn_lite.datasets" = ["*.csv"]
+"seaborn_lite.experiments" = ["*.txt"]

seaborn_lite-0.1.0/seaborn_lite/__init__.py

@@ -0,0 +1,85 @@
+"""seaborn-lite: a tiny matplotlib-only seaborn subset plus the DWM toolkit.
+
+Plot::
+
+    import seaborn_lite as snsl
+    snsl.histplot(df, x="Age", kde=True)
+
+Print an experiment write-up verbatim::
+
+    snsl.apriori()      # 05_APRIORI_FREQUENT_PATTERNS.txt
+    snsl.list()         # every experiment function
+
+Run an algorithm::
+
+    from seaborn_lite.dwm.itemsets import apriori, transactions_from_dataframe
+    from seaborn_lite import datasets
+    frequent = apriori(transactions_from_dataframe(datasets.load("transactions_list")), 0.3)
+"""
+from __future__ import annotations
+
+from . import datasets, dwm, experiments, plotting
+from .experiments import (
+    all_experiments,
+    apriori,
+    appriori,
+    categorical_naive_bayes,
+    data_preprocessing,
+    gaussian_naive_bayes,
+    hierarchical,
+    hierarchical_clustering,
+    hits,
+    kmeans,
+    kmedoids,
+    naive_bayes,
+    olap,
+    pagerank,
+    preprocessing,
+    sql,
+    star_schema,
+)
+from .experiments import list as list  # noqa: A001  (snsl.list(), as requested)
+from .plotting import (
+    barplot,
+    boxplot,
+    countplot,
+    heatmap,
+    histplot,
+    pairplot,
+    scatterplot,
+    set_theme,
+)
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "datasets",
+    "dwm",
+    "experiments",
+    "plotting",
+    "set_theme",
+    "histplot",
+    "countplot",
+    "barplot",
+    "boxplot",
+    "scatterplot",
+    "heatmap",
+    "pairplot",
+    "sql",
+    "star_schema",
+    "olap",
+    "preprocessing",
+    "data_preprocessing",
+    "apriori",
+    "appriori",
+    "kmeans",
+    "kmedoids",
+    "hierarchical",
+    "hierarchical_clustering",
+    "naive_bayes",
+    "categorical_naive_bayes",
+    "gaussian_naive_bayes",
+    "pagerank",
+    "hits",
+    "all_experiments",
+]

seaborn_lite-0.1.0/seaborn_lite/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+raise SystemExit(main())

seaborn_lite-0.1.0/seaborn_lite/cli.py

@@ -0,0 +1,49 @@
+"""Command line entry point: ``seaborn-lite``."""
+from __future__ import annotations
+
+import argparse
+
+from . import __version__, datasets
+from .demos import DEMOS, run_demo
+
+
+def main(argv=None) -> int:
+    parser = argparse.ArgumentParser(
+        prog="seaborn-lite",
+        description="Run the DWM practical-exam demos on bundled datasets.",
+    )
+    parser.add_argument("--version", action="version", version=f"seaborn-lite {__version__}")
+    sub = parser.add_subparsers(dest="command")
+
+    sub.add_parser("list", help="list available demos")
+    sub.add_parser("datasets", help="list bundled datasets")
+
+    run = sub.add_parser("run", help="run one demo")
+    run.add_argument("demo", choices=sorted(DEMOS), help="demo name")
+    run.add_argument("--data", help="path to a CSV (defaults to the bundled dataset)")
+    run.add_argument("--out", help="output directory or file for plots")
+
+    args = parser.parse_args(argv)
+
+    if args.command == "list":
+        print("Available demos:")
+        for name in sorted(DEMOS):
+            print(f"  {name}")
+        return 0
+
+    if args.command == "datasets":
+        print("Bundled datasets:")
+        for name in datasets.available():
+            print(f"  {name}")
+        return 0
+
+    if args.command == "run":
+        run_demo(args.demo, data=args.data, out=args.out)
+        return 0
+
+    parser.print_help()
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

seaborn_lite-0.1.0/seaborn_lite/datasets/__init__.py

@@ -0,0 +1,31 @@
+"""Bundled sample datasets, loadable by short name."""
+from __future__ import annotations
+
+from pathlib import Path
+
+import pandas as pd
+
+_DATA_DIR = Path(__file__).parent
+
+__all__ = ["available", "path", "load"]
+
+
+def available() -> list[str]:
+    """Names of every bundled dataset, without the ``.csv`` suffix."""
+    return sorted(p.stem for p in _DATA_DIR.glob("*.csv"))
+
+
+def path(name: str) -> Path:
+    """Absolute path of a bundled dataset; ``name`` may include ``.csv``."""
+    filename = name if name.endswith(".csv") else f"{name}.csv"
+    candidate = _DATA_DIR / filename
+    if not candidate.is_file():
+        raise FileNotFoundError(
+            f"Dataset {name!r} not found. Available: {', '.join(available())}"
+        )
+    return candidate
+
+
+def load(name: str, **kwargs) -> pd.DataFrame:
+    """Read a bundled dataset into a DataFrame (extra kwargs go to read_csv)."""
+    return pd.read_csv(path(name), **kwargs)

seaborn_lite-0.1.0/seaborn_lite/datasets/buy_computer.csv

@@ -0,0 +1,15 @@
+RID,Age_Group,Income,Student,Credit_Rating,Buy_Computer
+1,Youth,High,No,Fair,No
+2,Youth,High,No,Excellent,No
+3,Middle_Aged,High,No,Fair,Yes
+4,Senior,Medium,No,Fair,Yes
+5,Senior,Low,Yes,Fair,Yes
+6,Senior,Low,Yes,Excellent,No
+7,Middle_Aged,Low,Yes,Excellent,Yes
+8,Youth,Medium,No,Fair,No
+9,Youth,Low,Yes,Fair,Yes
+10,Senior,Medium,Yes,Fair,Yes
+11,Youth,Medium,Yes,Excellent,Yes
+12,Middle_Aged,Medium,No,Excellent,Yes
+13,Middle_Aged,High,Yes,Fair,Yes
+14,Senior,Medium,No,Excellent,No

seaborn_lite-0.1.0/seaborn_lite/datasets/customer_churn_raw.csv

@@ -0,0 +1,105 @@
+CustomerID,Age,Tenure_Months,Monthly_Charges,Contract_Type,Payment_Method,Churn
+CUST_0001,25.0,12.0,50.5,Month-to-month,Electronic check,No
+CUST_0002,30.0,24.0,70.0,One year,Mailed check,No
+CUST_0003,,36.0,85.2,Two year,Bank transfer,Yes
+CUST_0004,45.0,,110.0,Month-to-month,Credit card,No
+CUST_0005,22.0,6.0,,,Electronic check,Yes
+CUST_0006,19.0,1.0,20.0,Month-to-month,Electronic check,Yes
+CUST_0007,58.0,48.0,95.0,Two year,Mailed check,No
+CUST_0008,62.0,60.0,105.0,One year,Bank transfer,No
+CUST_0009,120.0,2.0,999.0,Month-to-month,Credit card,Yes
+CUST_0010,28.0,18.0,45.0,One year,Electronic check,No
+CUST_0011,35.0,20.0,65.0,Month-to-month,Electronic check,No
+CUST_0012,42.0,,75.0,One year,Mailed check,No
+CUST_0013,,5.0,80.0,Two year,Bank transfer,Yes
+CUST_0014,31.0,14.0,,Month-to-month,Credit card,No
+CUST_0015,29.0,28.0,55.0,,Electronic check,Yes
+CUST_0016,25.0,12.0,50.5,Month-to-month,Electronic check,Yes
+CUST_0017,30.0,24.0,70.0,Two year,Mailed check,No
+CUST_0018,,36.0,85.2,One year,Bank transfer,No
+CUST_0019,45.0,,110.0,Month-to-month,Credit card,Yes
+CUST_0020,22.0,6.0,,One year,Electronic check,No
+CUST_0021,19.0,1.0,20.0,Month-to-month,Electronic check,No
+CUST_0022,58.0,48.0,95.0,One year,Mailed check,No
+CUST_0023,62.0,60.0,105.0,Two year,Bank transfer,Yes
+CUST_0024,120.0,2.0,999.0,Month-to-month,Credit card,No
+CUST_0025,28.0,18.0,45.0,,Electronic check,Yes
+CUST_0026,35.0,20.0,65.0,Month-to-month,Electronic check,Yes
+CUST_0027,42.0,,75.0,Two year,Mailed check,No
+CUST_0028,,5.0,80.0,One year,Bank transfer,No
+CUST_0029,31.0,14.0,,Month-to-month,Credit card,Yes
+CUST_0030,29.0,28.0,55.0,One year,Electronic check,No
+CUST_0031,25.0,12.0,50.5,Month-to-month,Electronic check,No
+CUST_0032,30.0,24.0,70.0,One year,Mailed check,No
+CUST_0033,,36.0,85.2,Two year,Bank transfer,Yes
+CUST_0034,45.0,,110.0,Month-to-month,Credit card,No
+CUST_0035,22.0,6.0,,,Electronic check,Yes
+CUST_0036,19.0,1.0,20.0,Month-to-month,Electronic check,Yes
+CUST_0037,58.0,48.0,95.0,Two year,Mailed check,No
+CUST_0038,62.0,60.0,105.0,One year,Bank transfer,No
+CUST_0039,120.0,2.0,999.0,Month-to-month,Credit card,Yes
+CUST_0040,28.0,18.0,45.0,One year,Electronic check,No
+CUST_0041,35.0,20.0,65.0,Month-to-month,Electronic check,No
+CUST_0042,42.0,,75.0,One year,Mailed check,No
+CUST_0043,,5.0,80.0,Two year,Bank transfer,Yes
+CUST_0044,31.0,14.0,,Month-to-month,Credit card,No
+CUST_0045,29.0,28.0,55.0,,Electronic check,Yes
+CUST_0046,25.0,12.0,50.5,Month-to-month,Electronic check,Yes
+CUST_0047,30.0,24.0,70.0,Two year,Mailed check,No
+CUST_0048,,36.0,85.2,One year,Bank transfer,No
+CUST_0049,45.0,,110.0,Month-to-month,Credit card,Yes
+CUST_0050,22.0,6.0,,One year,Electronic check,No
+CUST_0051,19.0,1.0,20.0,Month-to-month,Electronic check,No
+CUST_0052,58.0,48.0,95.0,One year,Mailed check,No
+CUST_0053,62.0,60.0,105.0,Two year,Bank transfer,Yes
+CUST_0054,120.0,2.0,999.0,Month-to-month,Credit card,No
+CUST_0055,28.0,18.0,45.0,,Electronic check,Yes
+CUST_0056,35.0,20.0,65.0,Month-to-month,Electronic check,Yes
+CUST_0057,42.0,,75.0,Two year,Mailed check,No
+CUST_0058,,5.0,80.0,One year,Bank transfer,No
+CUST_0059,31.0,14.0,,Month-to-month,Credit card,Yes
+CUST_0060,29.0,28.0,55.0,One year,Electronic check,No
+CUST_0061,25.0,12.0,50.5,Month-to-month,Electronic check,No
+CUST_0062,30.0,24.0,70.0,One year,Mailed check,No
+CUST_0063,,36.0,85.2,Two year,Bank transfer,Yes
+CUST_0064,45.0,,110.0,Month-to-month,Credit card,No
+CUST_0065,22.0,6.0,,,Electronic check,Yes
+CUST_0066,19.0,1.0,20.0,Month-to-month,Electronic check,Yes
+CUST_0067,58.0,48.0,95.0,Two year,Mailed check,No
+CUST_0068,62.0,60.0,105.0,One year,Bank transfer,No
+CUST_0069,120.0,2.0,999.0,Month-to-month,Credit card,Yes
+CUST_0070,28.0,18.0,45.0,One year,Electronic check,No
+CUST_0071,35.0,20.0,65.0,Month-to-month,Electronic check,No
+CUST_0072,42.0,,75.0,One year,Mailed check,No
+CUST_0073,,5.0,80.0,Two year,Bank transfer,Yes
+CUST_0074,31.0,14.0,,Month-to-month,Credit card,No
+CUST_0075,29.0,28.0,55.0,,Electronic check,Yes
+CUST_0076,25.0,12.0,50.5,Month-to-month,Electronic check,Yes
+CUST_0077,30.0,24.0,70.0,Two year,Mailed check,No
+CUST_0078,,36.0,85.2,One year,Bank transfer,No
+CUST_0079,45.0,,110.0,Month-to-month,Credit card,Yes
+CUST_0080,22.0,6.0,,One year,Electronic check,No
+CUST_0081,19.0,1.0,20.0,Month-to-month,Electronic check,No
+CUST_0082,58.0,48.0,95.0,One year,Mailed check,No
+CUST_0083,62.0,60.0,105.0,Two year,Bank transfer,Yes
+CUST_0084,120.0,2.0,999.0,Month-to-month,Credit card,No
+CUST_0085,28.0,18.0,45.0,,Electronic check,Yes
+CUST_0086,35.0,20.0,65.0,Month-to-month,Electronic check,Yes
+CUST_0087,42.0,,75.0,Two year,Mailed check,No
+CUST_0088,,5.0,80.0,One year,Bank transfer,No
+CUST_0089,31.0,14.0,,Month-to-month,Credit card,Yes
+CUST_0090,29.0,28.0,55.0,One year,Electronic check,No
+CUST_0091,25.0,10.0,45.0,Month-to-month,Electronic check,No
+CUST_0092,30.0,12.0,55.0,One year,Mailed check,No
+CUST_0093,45.0,15.0,65.0,Two year,Bank transfer,Yes
+CUST_0094,50.0,20.0,75.0,Month-to-month,Credit card,No
+CUST_0095,22.0,25.0,85.0,,Electronic check,Yes
+CUST_0096,29.0,30.0,95.0,Month-to-month,Electronic check,Yes
+CUST_0097,31.0,35.0,60.0,Two year,Mailed check,No
+CUST_0098,40.0,40.0,70.0,One year,Bank transfer,No
+CUST_0099,38.0,45.0,80.0,Month-to-month,Credit card,Yes
+CUST_0100,36.0,50.0,90.0,One year,Electronic check,No
+CUST_0001,25.0,12.0,50.5,Month-to-month,Electronic check,No
+CUST_0002,30.0,24.0,70.0,One year,Mailed check,No
+CUST_0006,19.0,1.0,20.0,Month-to-month,Electronic check,Yes
+CUST_0013,,5.0,80.0,Two year,Bank transfer,Yes