add stats

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/*

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"]

frontend/clusters.py

@@ -0,0 +1,63 @@
+from sklearn.cluster import DBSCAN, KMeans
+import numpy as np
+
+class DBSCAN_cluster():
+    def __init__(self, eps, min_samples,data):
+        self.eps = eps
+        self.min_samples = min_samples
+        self.data = data
+        self.labels = np.array([])
+
+    def run(self):
+        dbscan = DBSCAN(eps=self.eps, min_samples=self.min_samples)
+        self.labels = dbscan.fit_predict(self.data)
+        return self.labels
+
+    def get_stats(self):
+        unique_labels = np.unique(self.labels)
+        stats = []
+        for label in unique_labels:
+            if label == -1:
+                continue
+            cluster_points = self.data[self.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
+    
+
+class KMeans_cluster():
+    def __init__(self, n_clusters, n_init, max_iter, data):
+        self.n_clusters = n_clusters
+        self.n_init = n_init
+        self.max_iter = max_iter
+        self.data = data
+        self.labels = np.array([])
+        self.centers = []
+
+    def run(self):
+        kmeans = KMeans(n_clusters=self.n_clusters, init="random", n_init=self.n_init, max_iter=self.max_iter, random_state=111)
+        self.labels = kmeans.fit_predict(self.data)
+        self.centers = kmeans.cluster_centers_
+        return self.labels
+
+
+    def get_stats(self):
+        unique_labels = np.unique(self.labels)
+        stats = []
+
+        for label in unique_labels:
+            cluster_points = self.data[self.labels == label]
+            num_points = len(cluster_points)
+            center = self.centers[label]
+            stats.append({
+                'cluster': label,
+                'num_points': num_points,
+                'center': center
+            })
+        return stats

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/normstrategy.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:

frontend/pages/clustering_dbscan.py

@@ -1,10 +1,9 @@
 import streamlit as st
 import matplotlib.pyplot as plt
-from sklearn.cluster import DBSCAN
+from clusters import DBSCAN_cluster
 
 st.header("Clustering: dbscan")
 
-
 if "data" in st.session_state:
     data = st.session_state.data
 
@@ -17,8 +16,9 @@ if "data" in st.session_state:
     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)
+        dbscan = DBSCAN_cluster(eps,min_samples,x)
+        y_dbscan = dbscan.run()
+        st.table(dbscan.get_stats())
 
         fig = plt.figure()
         if len(data_name) == 2:
@@ -28,8 +28,5 @@ if "data" in st.session_state:
             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

@@ -1,10 +1,9 @@
 import streamlit as st
-from sklearn.cluster import KMeans
 import matplotlib.pyplot as plt
+from clusters import KMeans_cluster
 
 st.header("Clustering: kmeans")
 
-
 if "data" in st.session_state:
     data = st.session_state.data
 
@@ -23,20 +22,21 @@ if "data" in st.session_state:
     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)
+        kmeans = KMeans_cluster(n_clusters, n_init, max_iter, x)
+        y_kmeans = kmeans.run()
 
+        st.table(kmeans.get_stats())
+
+        centers = kmeans.centers
         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)
 

frontend/pages/normalization.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from normstrategy import MVStrategy, ScalingStrategy
+from normstrategy import MVStrategy, ScalingStrategy, KNNStrategy
 
 if "data" in st.session_state:
     data = st.session_state.original_data
@@ -8,13 +8,16 @@ 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])
 

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