.drone.yml

@@ -1,44 +0,0 @@
-kind: pipeline
-name: default
-type: docker
-
-trigger:
-  event:
-    - push
-
-steps:
-  - name: lint
-    image: python:3.12
-    commands:
-      - pip install --root-user-action=ignore -r requirements.txt
-      - ruff check .
-
-  - name: docker-image
-    image: plugins/docker
-    settings:
-      dockerfile: Dockerfile
-      registry: hub.codefirst.iut.uca.fr
-      repo: hub.codefirst.iut.uca.fr/bastien.ollier/miner
-      username:
-        from_secret: REGISTRY_USER
-      password:
-        from_secret: REGISTRY_PASSWORD
-      cache_from:
-        - hub.codefirst.iut.uca.fr/bastien.ollier/miner:latest
-    depends_on: [ lint ]
-
-  - name: deploy-miner
-    image: hub.codefirst.iut.uca.fr/clement.freville2/codefirst-dockerproxy-clientdrone:latest
-    settings:
-      image: hub.codefirst.iut.uca.fr/bastien.ollier/miner:latest
-      container: miner
-      command: create
-      overwrite: true
-      admins: bastienollier,clementfreville2,hugopradier2
-    environment:
-      DRONE_REPO_OWNER: bastien.ollier
-    depends_on: [ docker-image ]
-    when:
-      branch:
-        - main
-        - ci/*

Dockerfile

@@ -1,9 +0,0 @@
-FROM python:3.12-slim
-
-WORKDIR /app
-
-COPY . . 
-RUN pip3 install -r requirements.txt
-
-EXPOSE 80
-ENTRYPOINT ["streamlit", "run", "frontend/exploration.py", "--server.port=80", "--server.address=0.0.0.0", "--server.baseUrlPath=/containers/bastienollier-miner"]

frontend/clusters.py

@@ -1,83 +0,0 @@
-from sklearn.cluster import DBSCAN, KMeans
-import numpy as np
-from dataclasses import dataclass
-from abc import ABC, abstractmethod
-from typing import Any, Optional
-
-@dataclass
-class ClusterResult:
-    labels: np.array
-    centers: Optional[np.array]
-    statistics: list[dict[str, Any]]
-
-
-class Cluster(ABC):
-    @abstractmethod
-    def run(self, data: np.array) -> ClusterResult:
-        pass
-
-
-class DBSCANCluster(Cluster):
-    def __init__(self, eps: float = 0.5, min_samples: int = 5):
-        self.eps = eps
-        self.min_samples = min_samples
-
-    #@typing.override
-    def run(self, data: np.array) -> ClusterResult:
-        dbscan = DBSCAN(eps=self.eps, min_samples=self.min_samples)
-        labels = dbscan.fit_predict(data)
-        return ClusterResult(labels, None, self.get_statistics(data, labels))
-
-    def get_statistics(self, data: np.array, labels: np.array) -> list[dict[str, Any]]:
-        unique_labels = np.unique(labels)
-        stats = []
-        for label in unique_labels:
-            if label == -1:
-                continue
-            cluster_points = data[labels == label]
-            num_points = len(cluster_points)
-            density = num_points / (np.max(cluster_points, axis=0) - np.min(cluster_points, axis=0)).prod()
-            stats.append({
-                "cluster": label,
-                "num_points": num_points,
-                "density": density
-            })
-        return stats
-
-    def __str__(self) -> str:
-        return "DBScan"
-
-
-class KMeansCluster(Cluster):
-    def __init__(self, n_clusters: int = 8, n_init: int = 1, max_iter: int = 300):
-        self.n_clusters = n_clusters
-        self.n_init = n_init
-        self.max_iter = max_iter
-
-    #@typing.override
-    def run(self, data: np.array) -> ClusterResult:
-        kmeans = KMeans(n_clusters=self.n_clusters, init="random", n_init=self.n_init, max_iter=self.max_iter, random_state=111)
-        labels = kmeans.fit_predict(data)
-        centers = kmeans.cluster_centers_
-        return ClusterResult(labels, centers, self.get_statistics(data, labels, centers))
-
-    def get_statistics(self, data: np.array, labels: np.array, centers: np.array) -> list[dict[str, Any]]:
-        unique_labels = np.unique(labels)
-        stats = []
-
-        for label in unique_labels:
-            cluster_points = data[labels == label]
-            num_points = len(cluster_points)
-            center = centers[label]
-            stats.append({
-                "cluster": label,
-                "num_points": num_points,
-                "center": center,
-            })
-        return stats
-
-    def __str__(self) -> str:
-        return "KMeans"
-
-
-CLUSTERING_STRATEGIES = [DBSCANCluster(), KMeansCluster()]

frontend/exploration.py

@@ -1,6 +1,5 @@
 import pandas as pd
 import streamlit as st
-import codecs
 
 st.set_page_config(
     page_title="Project Miner",
@@ -10,13 +9,10 @@ st.set_page_config(
 st.title("Home")
 
 ### Exploration
-uploaded_file = st.file_uploader("Upload your CSV file", type=["csv", "tsv"])
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
-separator = st.selectbox("Separator", [",", ";", "\\t"])
-separator = codecs.getdecoder("unicode_escape")(separator)[0]
-has_header = st.checkbox("Has header", value=True)
 
 if uploaded_file is not None:
-    st.session_state.data = pd.read_csv(uploaded_file, sep=separator, header=0 if has_header else 1)
+    st.session_state.data = pd.read_csv(uploaded_file)
     st.session_state.original_data = st.session_state.data
     st.success("File loaded successfully!")
 

frontend/normstrategy.py

@@ -1,7 +1,6 @@
 from abc import ABC, abstractmethod
 from pandas import DataFrame, Series
 from pandas.api.types import is_numeric_dtype
-from sklearn.neighbors import KNeighborsClassifier
 from typing import Any, Union
 
 class DataFrameFunction(ABC):
@@ -19,14 +18,11 @@ class MVStrategy(DataFrameFunction):
     """A way to handle missing values in a dataframe."""
 
     @staticmethod
-    def list_available(df: DataFrame, label: str, series: Series) -> list['MVStrategy']:
+    def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
         """Get all the strategies that can be used."""
         choices = [DropStrategy(), ModeStrategy()]
         if is_numeric_dtype(series):
             choices.extend((MeanStrategy(), MedianStrategy(), LinearRegressionStrategy()))
-            other_columns = df.select_dtypes(include="number").drop(label, axis=1).columns.to_list()
-            if len(other_columns):
-                choices.append(KNNStrategy(other_columns))
         return choices
 
 
@@ -101,43 +97,6 @@ class LinearRegressionStrategy(MVStrategy):
         return "Use linear regression"
 
 
-class KNNStrategy(MVStrategy):
-    def __init__(self, training_features: list[str]):
-        self.available_features = training_features
-        self.training_features = training_features
-        self.n_neighbors = 3
-
-    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
-        # Remove any training column that have any missing values
-        usable_data = df.dropna(subset=self.training_features)
-        # Select columns to impute from
-        train_data = usable_data.dropna(subset=label)
-        # Create train dataframe
-        x_train = train_data.drop(label, axis=1)
-        y_train = train_data[label]
-
-        reg = KNeighborsClassifier(self.n_neighbors).fit(x_train, y_train)
-
-        # Create test dataframe
-        test_data = usable_data[usable_data[label].isnull()]
-        if test_data.empty:
-            return df
-        x_test = test_data.drop(label, axis=1)
-        predicted = reg.predict(x_test)
-
-        # Fill with predicated values and patch the original data
-        usable_data[label].fillna(Series(predicted), inplace=True)
-        df.fillna(usable_data, inplace=True)
-        return df
-
-    def count_max(self, df: DataFrame, label: str) -> int:
-        usable_data = df.dropna(subset=self.training_features)
-        return usable_data[label].count()
-
-    def __str__(self) -> str:
-        return "kNN"
-
-
 class KeepStrategy(ScalingStrategy):
     #@typing.override
     def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:

frontend/pages/clustering.py

@@ -1,86 +0,0 @@
-import streamlit as st
-import matplotlib.pyplot as plt
-from clusters import DBSCANCluster, KMeansCluster, CLUSTERING_STRATEGIES
-from sklearn.decomposition import PCA
-from sklearn.metrics import silhouette_score
-import numpy as np
-
-st.header("Clustering")
-
-if "data" in st.session_state:
-    data = st.session_state.data
-
-    general_row = st.columns([1, 1, 1])
-    clustering = general_row[0].selectbox("Clustering method", CLUSTERING_STRATEGIES)
-    data_name = general_row[1].multiselect("Columns", data.select_dtypes(include="number").columns)
-    n_components = general_row[2].number_input("Reduce dimensions to (PCA)", min_value=1, max_value=3, value=2)
-
-    with st.form("cluster_form"):
-        if isinstance(clustering, KMeansCluster):
-            row1 = st.columns([1, 1, 1])
-            clustering.n_clusters = row1[0].number_input("Number of clusters", min_value=1, max_value=data.shape[0], value=clustering.n_clusters)
-            clustering.n_init = row1[1].number_input("n_init", min_value=1, value=clustering.n_init)
-            clustering.max_iter = row1[2].number_input("max_iter", min_value=1, value=clustering.max_iter)
-        elif isinstance(clustering, DBSCANCluster):
-            row1 = st.columns([1, 1])
-            clustering.eps = row1[0].slider("eps", min_value=0.0001, max_value=1.0, step=0.05, value=clustering.eps)
-            clustering.min_samples = row1[1].number_input("min_samples", min_value=1, value=clustering.min_samples)
-
-        st.form_submit_button("Launch")
-
-    if len(data_name) > 0:
-        x = data[data_name].to_numpy()
-        n_components = min(n_components, len(data_name))
-        if len(data_name) > n_components:
-            pca = PCA(n_components)
-            x = pca.fit_transform(x)
-            if n_components == 2:
-                (fig, ax) = plt.subplots(figsize=(8, 8))
-                for i in range(0, pca.components_.shape[1]):
-                    ax.arrow(
-                        0,
-                        0,
-                        pca.components_[0, i],
-                        pca.components_[1, i],
-                        head_width=0.1,
-                        head_length=0.1
-                    )
-
-                    plt.text(
-                        pca.components_[0, i] + 0.05,
-                        pca.components_[1, i] + 0.05,
-                        data_name[i]
-                    )
-                circle = plt.Circle((0, 0), radius=1, edgecolor='b', facecolor='None')
-                ax.add_patch(circle)
-                plt.axis("equal")
-                ax.set_title("PCA result - Correlation circle")
-                st.pyplot(fig)
-
-        result = clustering.run(x)
-        st.write("## Cluster stats")
-        st.table(result.statistics)
-
-        st.write("## Graphical representation")
-        fig = plt.figure()
-        if n_components == 1:
-            plt.scatter(x, np.zeros_like(x))
-        elif n_components == 2:
-            ax = fig.add_subplot(projection='rectilinear')
-            plt.scatter(x[:, 0], x[:, 1], c=result.labels, s=50, cmap="viridis")
-            if result.centers is not None:
-                plt.scatter(result.centers[:, 0], result.centers[:, 1], c="black", s=200, marker="X")
-        else:
-            ax = fig.add_subplot(projection='3d')
-
-            ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=result.labels, s=50, cmap="viridis")
-            if result.centers is not None:
-                ax.scatter(result.centers[:, 0], result.centers[:, 1], result.centers[:, 2], c="black", s=200, marker="X")
-        st.pyplot(fig)
-        if not (result.labels == 0).all():
-            st.write("Silhouette score:", silhouette_score(x, result.labels))
-    else:
-        st.error("Select at least one column")
-
-else:
-    st.error("file not loaded")

frontend/pages/clustering_dbscan.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import matplotlib.pyplot as plt
+from sklearn.cluster import DBSCAN
+
+st.header("Clustering: dbscan")
+
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("my_form"):
+        data_name = st.multiselect("Data Name", data.select_dtypes(include="number").columns, max_selections=3)
+        eps = st.slider("eps", min_value=0.0, max_value=1.0, value=0.5, step=0.01)
+        min_samples = st.number_input("min_samples", step=1, min_value=1, value=5)
+        st.form_submit_button("launch")
+
+    if len(data_name) >= 2 and len(data_name) <=3:
+        x = data[data_name].to_numpy()
+
+        dbscan = DBSCAN(eps=eps, min_samples=min_samples)
+        y_dbscan = dbscan.fit_predict(x)
+
+        fig = plt.figure()
+        if len(data_name) == 2:
+            ax = fig.add_subplot(projection='rectilinear')
+            plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis")
+        else:
+            ax = fig.add_subplot(projection='3d')
+            ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=y_dbscan, s=50, cmap="viridis")
+        st.pyplot(fig)
+
+    
+
+else:
+    st.error("file not loaded")

frontend/pages/clustering_kmeans.py

@@ -0,0 +1,44 @@
+import streamlit as st
+from sklearn.cluster import KMeans
+import matplotlib.pyplot as plt
+
+st.header("Clustering: kmeans")
+
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("my_form"):
+        row1 = st.columns([1,1,1])
+        n_clusters = row1[0].selectbox("Number of clusters", range(1,data.shape[0]))
+        data_name = row1[1].multiselect("Data Name",data.select_dtypes(include="number").columns, max_selections=3)
+        n_init = row1[2].number_input("n_init",step=1,min_value=1)
+
+        row2 = st.columns([1,1])
+        max_iter = row1[0].number_input("max_iter",step=1,min_value=1)
+
+
+        st.form_submit_button("launch")
+
+    if len(data_name) >= 2 and len(data_name) <=3:
+        x = data[data_name].to_numpy()
+
+        kmeans = KMeans(n_clusters=n_clusters, init="random", n_init=n_init, max_iter=max_iter, random_state=111)
+        y_kmeans = kmeans.fit_predict(x)
+
+        fig = plt.figure()
+        if len(data_name) == 2:
+            ax = fig.add_subplot(projection='rectilinear')
+            plt.scatter(x[:, 0], x[:, 1], c=y_kmeans, s=50, cmap="viridis")
+            centers = kmeans.cluster_centers_
+            plt.scatter(centers[:, 0], centers[:, 1], c="black", s=200, marker="X")
+        else:
+            ax = fig.add_subplot(projection='3d')
+
+            ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=y_kmeans, s=50, cmap="viridis")
+            centers = kmeans.cluster_centers_
+            ax.scatter(centers[:, 0], centers[:, 1],centers[:, 2], c="black", s=200, marker="X")
+        st.pyplot(fig)
+
+else:
+    st.error("file not loaded")

frontend/pages/normalization.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from normstrategy import MVStrategy, ScalingStrategy, KNNStrategy
+from normstrategy import MVStrategy, ScalingStrategy
 
 if "data" in st.session_state:
     data = st.session_state.original_data
@@ -8,16 +8,13 @@ if "data" in st.session_state:
     for column, series in data.items():
         col1, col2 = st.columns(2)
         missing_count = series.isna().sum()
-        choices = MVStrategy.list_available(data, column, series)
+        choices = MVStrategy.list_available(data, series)
         option = col1.selectbox(
             f"Missing values of {column} ({missing_count})",
             choices,
             index=1,
             key=f"mv-{column}",
         )
-        if isinstance(option, KNNStrategy):
-            option.training_features = st.multiselect("Training columns", option.training_features, default=option.available_features, key=f"cols-{column}")
-            option.n_neighbors = st.number_input("Number of neighbors", min_value=1, max_value=option.count_max(data, column), value=option.n_neighbors, key=f"neighbors-{column}")
         # Always re-get the series to avoid reusing an invalidated series pointer
         data = option.apply(data, column, data[column])
 

frontend/pages/prediction_classification.py

@@ -1,11 +1,9 @@
 import streamlit as st
 from sklearn.linear_model import LogisticRegression
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score,confusion_matrix
+from sklearn.metrics import accuracy_score
 from sklearn.preprocessing import LabelEncoder
 import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
 
 st.header("Prediction: Classification")
 
@@ -62,18 +60,5 @@ if "data" in st.session_state:
             prediction = label_encoders[target_name].inverse_transform(prediction)
         
         st.write("Prediction:", prediction[0])
-
-        if len(data_name) == 1:
-            fig = plt.figure()
-
-            y_pred = [model.predict(pd.DataFrame([pred_value[0]], columns=data_name)) for pred_value in X.values.tolist()]
-            cm = confusion_matrix(y, y_pred)
-
-            sns.heatmap(cm, annot=True, fmt="d")
-
-            plt.xlabel('Predicted')
-            plt.ylabel('True')
-
-            st.pyplot(fig)
 else:
     st.error("File not loaded")

frontend/pages/prediction_regression.py

@@ -1,8 +1,6 @@
 import streamlit as st
 from sklearn.linear_model import LinearRegression
-from sklearn.metrics import r2_score
 import pandas as pd
-import matplotlib.pyplot as plt
 
 st.header("Prediction: Regression")
 
@@ -27,37 +25,5 @@ if "data" in st.session_state:
         prediction = model.predict(pd.DataFrame([pred_values], columns=data_name))
 
         st.write("Prediction:", prediction[0])
-
-        fig = plt.figure()
-        dataframe_sorted = pd.concat([X, y], axis=1).sort_values(by=data_name)
-
-        if len(data_name) == 1:
-            y_pred = [model.predict(pd.DataFrame([pred_value[0]], columns=data_name)) for pred_value in X.values.tolist()]
-            r2 = r2_score(y, y_pred)
-            st.write('R-squared score:', r2)
-
-            X = dataframe_sorted[data_name[0]]
-            y = dataframe_sorted[target_name]
-
-            prediction_array_y = [
-                model.predict(pd.DataFrame([[dataframe_sorted[data_name[0]].iloc[i]]], columns=data_name))[0]
-                for i in range(dataframe_sorted.shape[0])
-            ]
-
-            plt.scatter(dataframe_sorted[data_name[0]], dataframe_sorted[target_name], color='b')
-            plt.plot(dataframe_sorted[data_name[0]], prediction_array_y, color='r')
-        elif len(data_name) == 2:
-            ax = fig.add_subplot(111, projection='3d')
-
-            prediction_array_y = [
-                model.predict(pd.DataFrame([[dataframe_sorted[data_name[0]].iloc[i], dataframe_sorted[data_name[1]].iloc[i]]], columns=data_name))[0]
-                for i in range(dataframe_sorted.shape[0])
-            ]
-
-            ax.scatter(dataframe_sorted[data_name[0]], dataframe_sorted[data_name[1]], dataframe_sorted[target_name], color='b')
-            ax.plot(dataframe_sorted[data_name[0]], dataframe_sorted[data_name[1]], prediction_array_y, color='r')
-
-        st.pyplot(fig)
-
 else:
     st.error("File not loaded")

requirements.txt

@@ -1,6 +0,0 @@
-matplotlib>=3.5.0
-pandas>=1.5.0
-seaborn>=0.12.0
-scikit-learn>=0.23.0
-streamlit>=1.35.0
-ruff>=0.4.8