data-science-concepts 2026.0.0__py3-none-any.whl

data_science_concepts/__init__.py

@@ -0,0 +1,8 @@
+"""Helper functions for the Concepts in Data Science practicals (Wageningen University)."""
+from importlib.metadata import version
+
+from .decision_boundary import plot_decision_boundary
+from .pca_example import make_pca_example_figure
+
+__version__ = version("data-science-concepts")
+__all__ = ["make_pca_example_figure", "plot_decision_boundary"]

data_science_concepts/decision_boundary.py

@@ -0,0 +1,31 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import seaborn as sns
+
+
+def plot_decision_boundary(X, y, feature_names, clf, ax=None, proba=True):
+    """
+    Utility function for plotting a binary classication boundary in a 2D dataset
+    This function does not work for any other classification problem (e.g. multiclass) or feature dimensionality
+    """
+    if ax is None:
+        fig, ax = plt.subplots(figsize=(10,10))
+    # Plot the decision boundary by assigning a color to each point in the mesh [x_min, x_max]x[y_min, y_max].
+    x_min, x_max = X[feature_names[0]].min() - 1, X[feature_names[0]].max() + 1
+    y_min, y_max = X[feature_names[1]].min() - 1, X[feature_names[1]].max() + 1
+    step = 0.05
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, step),
+                         np.arange(y_min, y_max, step))
+
+    # Predict on all data points
+    if proba:
+        Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
+    else:
+        Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
+        
+    # Put the result into a color plot
+    Z = Z.reshape(xx.shape)
+    ax.contourf(xx, yy, Z, alpha=0.6, cmap="RdYlBu_r")
+
+    # Plot data points
+    sns.scatterplot(data=X, x=feature_names[0], y=feature_names[1], hue=y, s=30, palette="RdYlBu_r", ax=ax, edgecolor='black')

data_science_concepts/pca_example.py

@@ -0,0 +1,148 @@
+import numpy as np
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+from sklearn.decomposition import PCA
+
+
+def make_pca_example_figure():
+    """Interactive figure of PCA on a simulated 3D dataset: the data space with the
+    first two principal components (left) and the projection onto those components (right)."""
+    np.random.seed(0)
+    X1 = np.random.normal(0, 15, 50)
+    X2 = X1 + np.random.normal(0, 10, 50)
+    X3 = X1 + np.random.normal(0, 10, 50)
+
+    dat = np.array([X1, X2, X3]).T
+    mu = dat.mean(axis=0)
+
+    n_comp = 2
+
+    pca = PCA(n_components=2).fit(dat)
+    latent_points = pca.transform(dat).T
+
+    pc1_latent = np.array([
+        [0, -30],
+        [0, 30]
+    ])
+    pc1 = np.dot(pc1_latent, pca.components_[:n_comp,:]) + mu[0]
+
+    pc2_latent = np.array([
+        [-80, 0],
+        [80, 0]
+    ])
+    pc2 = np.dot(pc2_latent, pca.components_[:n_comp,:]) + mu[1]
+
+    fig = make_subplots(
+        specs=[[
+            dict(type='scene'),
+            dict(type='xy')
+        ]],
+        subplot_titles=['Data space (3D)', 'Principal Component space (2D)'],
+        rows=1, 
+        cols=2)
+
+    # Data space (3D)
+    fig.add_trace(
+        go.Scatter3d(
+            x=X1,
+            y=X2,
+            z=X3,
+            mode='markers',
+            marker=dict(
+                size=4,
+                color='darkblue',
+                opacity=.7
+            ),
+            showlegend=False
+        ),
+        row=1,col=1
+    )
+
+    fig.add_trace(
+        go.Scatter3d(
+            x=pc1.T[0],
+            y=pc1.T[1],
+            z=pc1.T[2],
+            mode='lines',
+            marker=dict(
+                color='orange'
+            ),
+            showlegend=False
+        ),
+        row=1,col=1
+    )
+
+    fig.add_trace(
+        go.Scatter3d(
+            x=pc2.T[0],
+            y=pc2.T[1],
+            z=pc2.T[2],
+            mode='lines',
+            marker=dict(
+                color='darkgreen'
+            ),
+            showlegend=False
+        ),
+        row=1,col=1
+    )
+
+    # Latent space (2D)
+    fig.add_trace(
+        go.Scatter(
+            x=latent_points[0], 
+            y=latent_points[1], 
+            mode='markers',
+            marker=dict(
+                size=8,
+                color='darkblue',
+                opacity=.7
+            ),
+            showlegend=False
+        ),
+        row=1,
+        col=2
+    )
+
+    fig.add_trace(
+        go.Scatter(
+            x=pc1_latent.T[0],
+            y=pc1_latent.T[1],
+            mode='lines',
+            marker=dict(
+                color='orange'
+            ),
+            showlegend=False
+        ),
+        row=1,col=2
+    )
+
+    fig.add_trace(
+        go.Scatter(
+            x=pc2_latent.T[0],
+            y=pc2_latent.T[1],
+            mode='lines',
+            marker=dict(
+                color='darkgreen'
+            ),
+            showlegend=False
+        ),
+        row=1,col=2
+    )
+
+    fig.update_xaxes(
+        title_text=f'PC1 ({pca.explained_variance_ratio_[0] * 100:.4}% variance)', 
+        range=(-100, 100), 
+        row=1, 
+        col=2
+    )
+    fig.update_yaxes(
+        title_text=f'PC2 ({pca.explained_variance_ratio_[1] * 100:.3}% variance)', 
+        range=(-50, 50), 
+        row=1, 
+        col=2
+    )
+
+
+    fig.update_layout(margin=dict(l=0, r=40, b=100, t=100))
+    #fig.show()
+    return fig

data_science_concepts-2026.0.0.dist-info/METADATA

@@ -0,0 +1,79 @@
+Metadata-Version: 2.5
+Name: data-science-concepts
+Version: 2026.0.0
+Summary: Helper functions for the Concepts in Data Science practicals (Wageningen University)
+Project-URL: Repository, https://github.com/wur-bioinformatics/data-science-concepts
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: plotly
+Requires-Dist: scikit-learn
+Requires-Dist: seaborn
+Description-Content-Type: text/markdown
+
+# _INF34306_ Concepts in Data Science
+
+Notebooks and datasets for Concepts in Data Science practicals.
+
+### Using the notebooks
+
+The notebooks are meant to be used in [Google Colab](https://colab.research.google.com). Open a notebook with one of the links below, then use *File → Save a copy in Drive* to keep your changes.
+
+| Block | Tutorial | Project |
+|---|---|---|
+| 1 - Introduction | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block1_introduction/tutorial_1.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block1_introduction/project_1.ipynb) |
+| 2 - Python libraries, Visualization, and the Grammar of Graphics | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block2_visualisation/tutorial_2.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block2_visualisation/project_2.ipynb) |
+| 3 - Data exploration I | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block3_exploration_1/tutorial_3.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block3_exploration_1/project_3.ipynb) |
+| 4 - Data exploration II | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block4_exploration_2/tutorial_4.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/wur-bioinformatics/data-science-concepts/blob/main/notebooks/block4_exploration_2/project_4.ipynb) |
+
+In blocks 1 and 2, students download the datasets from Kaggle themselves and upload them to Colab (`files.upload()`). From block 3 onwards, the notebooks read datasets directly from this repository on GitHub (`DATA_URL` in the notebooks). Note that this points to the `main` branch: files that are not on `main` yet will not load.
+
+### Repository structure
+
+Notebooks with exercises and examples are in the `notebooks` folder, with one subfolder per block. Datasets (when not available through APIs) are in the `datasets` folder, with informative filenames.
+
+```
+|-- README.md
+|-- TODO.md
+|-- datasets
+|   |-- UniComplaints.csv
+|   |-- anscombe_quartet.csv
+|   |-- automobile.csv
+|   |-- breast-cancer.csv
+|   |-- iris.csv
+|   |-- titanic.csv
+|   |-- top_1000_popular_movies_tmdb.csv
+|   `-- ... (not used by the current notebooks, see TODO.md)
+|-- notebooks
+|   |-- block1_introduction
+|   |   |-- tutorial_1.ipynb
+|   |   `-- project_1.ipynb
+|   |-- block2_visualisation
+|   |   |-- tutorial_2.ipynb
+|   |   `-- project_2.ipynb
+|   |-- block3_exploration_1
+|   |   |-- tutorial_3.ipynb
+|   |   `-- project_3.ipynb
+|   `-- block4_exploration_2
+|       |-- tutorial_4.ipynb
+|       `-- project_4.ipynb
+|-- pyproject.toml
+|-- requirements.txt
+`-- src
+    `-- data_science_concepts   (course package, see below)
+```
+
+Images used in the notebooks are stored next to the notebooks and linked by their GitHub URL, because Colab does not resolve relative image paths.
+
+### Course package
+
+Helper functions used in the notebooks (e.g. `plot_decision_boundary`) are in the `data-science-concepts` package in `src/data_science_concepts`. The notebooks install it with
+
+```python
+%pip install -q "data-science-concepts==2026.*"
+import data_science_concepts as dsc
+```
+
+To release a new version, create a GitHub release with a tag of the form `vYEAR.MINOR.PATCH` (e.g. `v2026.0.1`). The `Package` workflow (`.github/workflows/package.yml`) builds the package and publishes it to [PyPI](https://pypi.org/project/data-science-concepts/); the version number is taken from the tag. Notebooks pin the course year, so a release for the next year (`v2027.0.0`) does not affect notebooks of the current year.

data_science_concepts-2026.0.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+data_science_concepts/__init__.py,sha256=YmDZwG97UYvSuS-zTy166BMr26f5kHL_za7eh_G3ZzQ,347
+data_science_concepts/decision_boundary.py,sha256=Q2BDFcHb2Ee2sU1sWIHVH-684xRdWHxvv_kGUBfFdUs,1288
+data_science_concepts/pca_example.py,sha256=PN_WHpgvLPuW-Hy23HH-p3MhVOIMUcordpTQMF3isFU,3360
+data_science_concepts-2026.0.0.dist-info/METADATA,sha256=tKM-FnU96O-RMIOaf0L_DqfHPEYfinr1XQaqiVNITEc,4940
+data_science_concepts-2026.0.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+data_science_concepts-2026.0.0.dist-info/licenses/LICENSE,sha256=FofaOuRtJbvHY4QxuOEvcqg9S7aTER1dJhdlOtxHA_g,1075
+data_science_concepts-2026.0.0.dist-info/RECORD,,

data_science_concepts-2026.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.4
+Root-Is-Purelib: true
+Tag: py3-none-any

data_science_concepts-2026.0.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 WUR Bioinformatics
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.