ml-lab-prep 0.2.0__tar.gz → 0.3.2__tar.gz

ml_lab_prep-0.3.2/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: ml-lab-prep
+Version: 0.3.2
+Summary: 4 bare-bones ML lab pipeline notebooks 
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# ml-lab-prep
+
+Four ML lab pipeline notebooks (spam classification, breast cancer ensembles, loan regression, K-Means).
+
+```bash
+pip install ml-lab-prep
+ml-lab
+```
+
+Pick with up/down and space, press enter. The notebooks are saved in the current folder.
+
+Without the picker: `ml-lab init spam loan` (keys: spam, cancer, loan, kmeans) or `ml-lab init --all`.

ml_lab_prep-0.3.2/README.md

@@ -0,0 +1,12 @@
+# ml-lab-prep
+
+Four ML lab pipeline notebooks (spam classification, breast cancer ensembles, loan regression, K-Means).
+
+```bash
+pip install ml-lab-prep
+ml-lab
+```
+
+Pick with up/down and space, press enter. The notebooks are saved in the current folder.
+
+Without the picker: `ml-lab init spam loan` (keys: spam, cancer, loan, kmeans) or `ml-lab init --all`.

{ml_lab_prep-0.2.0 → ml_lab_prep-0.3.2}/pyproject.toml

@@ -4,17 +4,18 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ml-lab-prep"
-version = "0.2.0"
-description = "4 bare-bones ML lab pipeline notebooks with an interactive picker"
+version = "0.3.2"
+description = "4 bare-bones ML lab pipeline notebooks "
 readme = "README.md"
 requires-python = ">=3.9"
-dependencies = ["numpy", "pandas", "scikit-learn>=1.2", "scipy", "matplotlib", "seaborn"]
+dependencies = []
 
 [project.scripts]
 ml-lab-prep = "ml_lab_prep.cli:main"
+ml-lab = "ml_lab_prep.cli:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]
 
 [tool.setuptools.package-data]
-ml_lab_prep = ["content/*.ipynb", "content/*.md", "content/*.txt", "content/data/*.csv"]
+ml_lab_prep = ["content/*.ipynb"]

ml_lab_prep-0.3.2/src/ml_lab_prep/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.2"

{ml_lab_prep-0.2.0 → ml_lab_prep-0.3.2}/src/ml_lab_prep/cli.py

@@ -2,11 +2,11 @@ import argparse, curses, shutil, sys
 from importlib.resources import files
 from pathlib import Path
 
-ITEMS = {  # key: (notebook, dataset, description)
-    "spam":    ("01_Spambase_Classification.ipynb",    "spambase.csv",      "Spam vs ham: Decision Tree, KNN, SVM"),
-    "cancer":  ("02_BreastCancer_Classification.ipynb", "breast_cancer.csv", "Breast cancer: Decision Tree, Random Forest, Gradient Boosting"),
-    "loan":    ("03_LoanAmount_Regression.ipynb",       "loan_data.csv",     "Loan amount regression: Linear, Ridge, Random Forest"),
-    "kmeans":  ("04_KMeans_Clustering.ipynb",           "breast_cancer.csv", "K-Means clustering + PCA"),
+ITEMS = {  # key: (notebook, description)
+    "spam":    ("01_Spambase_Classification.ipynb", "Spam vs ham: Decision Tree, KNN, SVM"),
+    "cancer":  ("02_BreastCancer_Classification.ipynb", "Breast cancer: Decision Tree, Random Forest, AdaBoost, Gradient Boosting, XGBoost"),
+    "loan":    ("03_LoanAmount_Regression.ipynb", "Loan regression: Linear, Ridge, Lasso, ElasticNet, Random Forest"),
+    "kmeans":  ("04_KMeans_Clustering.ipynb", "K-Means clustering + PCA"),
 }
 
 
@@ -21,7 +21,7 @@ def pick():
             scr.addstr(0, 0, "ml-lab-prep   up/down move | space select | a all | enter download | q quit")
             for i, k in enumerate(keys):
                 mark = "[x]" if k in on else "[ ]"
-                line = f" {mark} {ITEMS[k][0]:<40} {ITEMS[k][2]}"
+                line = f" {mark} {ITEMS[k][0]:<40} {ITEMS[k][1]}"
                 scr.addstr(2 + i, 0, line[: curses.COLS - 1], curses.A_REVERSE if i == cur else 0)
             scr.refresh()
             c = scr.getch()
@@ -37,15 +37,11 @@ def pick():
 
 def download(keys, dest):
     src, dest = files("ml_lab_prep") / "content", Path(dest)
-    (dest / "data").mkdir(parents=True, exist_ok=True)
-    for name in ("README.md", "requirements.txt"):
-        shutil.copy(src / name, dest / name)
+    dest.mkdir(parents=True, exist_ok=True)
     for k in keys:
-        nb, csv, _ = ITEMS[k]
-        shutil.copy(src / nb, dest / nb)
-        shutil.copy(src / "data" / csv, dest / "data" / csv)
-        print("  added", nb)
-    print(f"\nDone -> {dest.resolve()}\nNext: cd {dest}  &&  jupyter notebook")
+        shutil.copy(src / ITEMS[k][0], dest / ITEMS[k][0])
+        print("  added", ITEMS[k][0])
+    print("\nSaved in", dest.resolve())
 
 
 def main():
@@ -53,10 +49,10 @@ def main():
     ap.add_argument("cmd", nargs="?", default="init", choices=["init", "list"])
     ap.add_argument("names", nargs="*", help="spam cancer loan kmeans (omit to pick interactively)")
     ap.add_argument("--all", action="store_true", help="download all 4")
-    ap.add_argument("-d", "--dest", default="ml_lab", help="target folder (default: ml_lab)")
+    ap.add_argument("-d", "--dest", default=".", help="target folder (default: current folder)")
     a = ap.parse_args()
     if a.cmd == "list":
-        for k, v in ITEMS.items(): print(f"{k:8s}{v[0]:42s}{v[2]}")
+        for k, v in ITEMS.items(): print(f"{k:8s}{v[0]:42s}{v[1]}")
         return
     keys = list(ITEMS) if a.all else a.names
     bad = [k for k in keys if k not in ITEMS]