correctifs pour lint

Co-authored-by: clfreville2 <clement.freville2@etu.uca.fr>
Co-authored-by: bastien ollier <bastien.ollier@etu.uca.fr>
Reviewed-on: https://codefirst.iut.uca.fr/git/clement.freville2/miner/pulls/9
Reviewed-by: Clément FRÉVILLE <clement.freville2@etu.uca.fr>
Co-authored-by: Bastien OLLIER <bastien.ollier@noreply.codefirst.iut.uca.fr>
Co-committed-by: Bastien OLLIER <bastien.ollier@noreply.codefirst.iut.uca.fr>

.drone.yml

@@ -0,0 +1,44 @@
+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/*

.gitignore

@@ -1 +1,2 @@
 __pycache__
+*/myenv

Dockerfile

@@ -0,0 +1,9 @@
+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"]

backend/classification_strategy.py

@@ -0,0 +1,45 @@
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from sklearn.preprocessing import LabelEncoder
+
+def perform_classification(data, data_name, target_name, test_size):
+    X = data[data_name]
+    y = data[target_name]
+
+    label_encoders = {}
+    for column in X.select_dtypes(include=['object']).columns:
+        le = LabelEncoder()
+        X[column] = le.fit_transform(X[column])
+        label_encoders[column] = le
+
+    if y.dtype == 'object':
+        le = LabelEncoder()
+        y = le.fit_transform(y)
+        label_encoders[target_name] = le
+    else:
+        if y.nunique() > 10:
+            raise ValueError("The target variable seems to be continuous. Please select a categorical target for classification.")
+    
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)
+
+    model = LogisticRegression()
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+    accuracy = accuracy_score(y_test, y_pred)
+
+    return model, label_encoders, accuracy
+
+def make_prediction(model, label_encoders, data_name, target_name, input_values):
+    X_new = []
+    for feature, value in zip(data_name, input_values):
+        if feature in label_encoders:
+            value = label_encoders[feature].transform([value])[0]
+        X_new.append(value)
+    
+    prediction = model.predict([X_new])
+
+    if target_name in label_encoders:
+        prediction = label_encoders[target_name].inverse_transform(prediction)
+    
+    return prediction[0]

backend/dbscan_strategy.py

@@ -0,0 +1,16 @@
+import matplotlib.pyplot as plt
+from sklearn.cluster import DBSCAN
+
+def perform_dbscan_clustering(data, data_name, eps, min_samples):
+    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")
+    return fig

backend/kmeans_strategy.py

@@ -0,0 +1,20 @@
+import matplotlib.pyplot as plt
+from sklearn.cluster import KMeans
+
+def perform_kmeans_clustering(data, data_name, n_clusters, n_init, max_iter):
+    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")
+    return fig

backend/norm_strategy.py

@@ -1,6 +1,7 @@
 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):
@@ -18,11 +19,14 @@ class MVStrategy(DataFrameFunction):
     """A way to handle missing values in a dataframe."""
 
     @staticmethod
-    def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
+    def list_available(df: DataFrame, label: str, 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
 
 
@@ -97,6 +101,43 @@ 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:

backend/regression_strategy.py

@@ -0,0 +1,18 @@
+from sklearn.linear_model import LinearRegression
+
+def perform_regression(data, data_name, target_name):
+    X = data[data_name]
+    y = data[target_name]
+
+    if not isinstance(y.iloc[0], (int, float)):
+        raise ValueError("The target variable should be numeric (continuous) for regression.")
+
+    model = LinearRegression()
+    model.fit(X, y)
+    
+    return model
+
+def make_prediction(model, feature_names, input_values):
+    prediction = model.predict([input_values])
+
+    return prediction[0]

backend/visualization_strategy.py

@@ -0,0 +1,16 @@
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+def plot_histogram(data, column):
+    fig, ax = plt.subplots()
+    ax.hist(data[column].dropna(), bins=20, edgecolor='k')
+    ax.set_title(f"Histogram of {column}")
+    ax.set_xlabel(column)
+    ax.set_ylabel("Frequency")
+    return fig
+
+def plot_boxplot(data, column):
+    fig, ax = plt.subplots()
+    sns.boxplot(data=data, x=column, ax=ax)
+    ax.set_title(f"Boxplot of {column}")
+    return fig

frontend/exploration.py

@@ -1,5 +1,6 @@
 import pandas as pd
 import streamlit as st
+import codecs
 
 st.set_page_config(
     page_title="Project Miner",
@@ -9,10 +10,13 @@ st.set_page_config(
 st.title("Home")
 
 ### Exploration
-uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv", "tsv"])
+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)
+    st.session_state.data = pd.read_csv(uploaded_file, sep=separator, header=0 if has_header else 1)
     st.session_state.original_data = st.session_state.data
     st.success("File loaded successfully!")
 

frontend/pages/clustering:_kmeans.py

@@ -1,44 +0,0 @@
-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/clustering_dbscan.py

@@ -1,35 +1,22 @@
 import streamlit as st
-import matplotlib.pyplot as plt
+import sys
-from sklearn.cluster import DBSCAN
+import os
-
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
-st.header("Clustering: dbscan")
+from dbscan_strategy import perform_dbscan_clustering
 
+st.header("Clustering: DBSCAN")
 
 if "data" in st.session_state:
     data = st.session_state.data
 
-    with st.form("my_form"):
+    with st.form("dbscan_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")
+        submitted = st.form_submit_button("Launch")
 
-    if len(data_name) >= 2 and len(data_name) <=3:
+    if submitted and 2 <= len(data_name) <= 3:
-        x = data[data_name].to_numpy()
+        fig = perform_dbscan_clustering(data, data_name, eps, min_samples)
-
-        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")
+    st.error("File not loaded")

frontend/pages/clustering_kmeans.py

@@ -0,0 +1,26 @@
+import streamlit as st
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
+from kmeans_strategy import perform_kmeans_clustering
+
+st.header("Clustering: KMeans")
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("kmeans_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 = row2[0].number_input("max_iter", step=1, min_value=1)
+        submitted = st.form_submit_button("Launch")
+
+    if submitted and 2 <= len(data_name) <= 3:
+        fig = perform_kmeans_clustering(data, data_name, n_clusters, n_init, max_iter)
+        st.pyplot(fig)
+else:
+    st.error("File not loaded")

frontend/pages/normalization.py

@@ -1,5 +1,8 @@
 import streamlit as st
-from normstrategy import MVStrategy, ScalingStrategy
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
+from norm_strategy import MVStrategy, ScalingStrategy, KNNStrategy
 
 if "data" in st.session_state:
     data = st.session_state.original_data
@@ -8,13 +11,16 @@ 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, series)
+        choices = MVStrategy.list_available(data, column, 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

@@ -0,0 +1,48 @@
+import streamlit as st
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
+from classification_strategy import perform_classification, make_prediction
+
+st.header("Prediction: Classification")
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("classification_form"):
+        st.subheader("Classification Parameters")
+        data_name = st.multiselect("Features", data.columns, key="classification_features")
+        target_name = st.selectbox("Target", data.columns, key="classification_target")
+        test_size = st.slider("Test Size", min_value=0.1, max_value=0.5, value=0.2, step=0.1, key="classification_test_size")
+        submitted = st.form_submit_button('Train and Predict')
+
+    if submitted and data_name and target_name:
+        try:
+            model, label_encoders, accuracy = perform_classification(data, data_name, target_name, test_size)
+            st.session_state.classification_model = model
+            st.session_state.classification_label_encoders = label_encoders
+            st.session_state.classification_accuracy = accuracy
+            st.session_state.classification_features_selected = data_name
+            st.session_state.classification_target_selected = target_name
+        except ValueError as e:
+            st.error(e)
+
+    if "classification_model" in st.session_state:
+        st.subheader("Model Accuracy")
+        st.write(f"Accuracy on test data: {st.session_state.classification_accuracy:.2f}")
+
+        st.subheader("Enter values for prediction")
+        input_values = []
+        for feature in st.session_state.classification_features_selected:
+            if feature in st.session_state.classification_label_encoders:
+                values = list(st.session_state.classification_label_encoders[feature].classes_)
+                value = st.selectbox(f"Value for {feature}", values, key=f"classification_input_{feature}")
+            else:
+                value = st.number_input(f"Value for {feature}", value=0.0, key=f"classification_input_{feature}")
+            input_values.append(value)
+
+        prediction = make_prediction(st.session_state.classification_model, st.session_state.classification_label_encoders, st.session_state.classification_features_selected, st.session_state.classification_target_selected, input_values)
+        
+        st.write("Prediction:", prediction)
+else:
+    st.error("File not loaded")

frontend/pages/prediction_regression.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
+from regression_strategy import perform_regression, make_prediction
+
+st.header("Prediction: Regression")
+
+if "data" in st.session_state:
+    data = st.session_state.data
+
+    with st.form("regression_form"):
+        st.subheader("Linear Regression Parameters")
+        data_name = st.multiselect("Features", data.select_dtypes(include="number").columns, key="regression_features")
+        target_name = st.selectbox("Target", data.select_dtypes(include="number").columns, key="regression_target")
+        submitted = st.form_submit_button('Train and Predict')
+
+    if submitted and data_name and target_name:
+        try:
+            model = perform_regression(data, data_name, target_name)
+            st.session_state.regression_model = model
+            st.session_state.regression_features_selected = data_name
+            st.session_state.regression_target_selected = target_name
+        except ValueError as e:
+            st.error(e)
+
+    if "regression_model" in st.session_state:
+        st.subheader("Enter values for prediction")
+        input_values = [st.number_input(f"Value for {feature}", value=0.0, key=f"regression_input_{feature}") for feature in st.session_state.regression_features_selected]
+        prediction = make_prediction(st.session_state.regression_model, st.session_state.regression_features_selected, input_values)
+
+        st.write("Prediction:", prediction)
+else:
+    st.error("File not loaded")

frontend/pages/visualization.py

@@ -1,30 +1,25 @@
 import streamlit as st
-import matplotlib.pyplot as plt
+import sys
-import seaborn as sns
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../../backend')))
+from visualization_strategy import plot_histogram, plot_boxplot
 
 st.header("Data Visualization")
 
-
 if "data" in st.session_state:
     data = st.session_state.data
 
     st.subheader("Histogram")
     column_to_plot = st.selectbox("Select Column for Histogram", data.columns)
     if column_to_plot:
-        fig, ax = plt.subplots()
+        fig = plot_histogram(data, column_to_plot)
-        ax.hist(data[column_to_plot].dropna(), bins=20, edgecolor='k')
-        ax.set_title(f"Histogram of {column_to_plot}")
-        ax.set_xlabel(column_to_plot)
-        ax.set_ylabel("Frequency")
         st.pyplot(fig)
 
     st.subheader("Boxplot")
     dataNumeric = data.select_dtypes(include="number")
     column_to_plot = st.selectbox("Select Column for Boxplot", dataNumeric.columns)
     if column_to_plot:
-        fig, ax = plt.subplots()
+        fig = plot_boxplot(data, column_to_plot)
-        sns.boxplot(data=data, x=column_to_plot, ax=ax)
-        ax.set_title(f"Boxplot of {column_to_plot}")
         st.pyplot(fig)
 else:
     st.error("file not loaded")

requirements.txt

@@ -0,0 +1,6 @@
+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