Support multiple column delimiters

Reviewed-on: https://codefirst.iut.uca.fr/git/clement.freville2/miner/pulls/8

.gitignore

@@ -1 +1,2 @@
 __pycache__
+.venv

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

@@ -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
+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])
 

frontend/pages/prediction_classification.py

@@ -0,0 +1,64 @@
+import streamlit as st
+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
+import pandas as pd
+
+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)
+        target_name = st.selectbox("Target", data.columns)
+        test_size = st.slider("Test Size", min_value=0.1, max_value=0.5, value=0.2, step=0.1)
+        st.form_submit_button('Train and Predict')
+
+    if data_name and target_name:
+        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
+
+        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)
+
+        st.subheader("Model Accuracy")
+        st.write(f"Accuracy on test data: {accuracy:.2f}")
+
+        st.subheader("Enter values for prediction")
+        pred_values = []
+        for feature in data_name:
+            if feature in label_encoders:
+                values = list(label_encoders[feature].classes_)
+                value = st.selectbox(f"Value for {feature}", values)
+                value_encoded = label_encoders[feature].transform([value])[0]
+                pred_values.append(value_encoded)
+            else:
+                value = st.number_input(f"Value for {feature}", value=0.0)
+                pred_values.append(value)
+        
+        prediction = model.predict(pd.DataFrame([pred_values], columns=data_name))
+
+        if target_name in label_encoders:
+            prediction = label_encoders[target_name].inverse_transform(prediction)
+        
+        st.write("Prediction:", prediction[0])
+else:
+    st.error("File not loaded")

frontend/pages/prediction_regression.py

@@ -0,0 +1,29 @@
+import streamlit as st
+from sklearn.linear_model import LinearRegression
+import pandas as pd
+
+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)
+        target_name = st.selectbox("Target", data.select_dtypes(include="number").columns)
+        st.form_submit_button('Train and Predict')
+
+    if data_name and target_name:
+        X = data[data_name]
+        y = data[target_name]
+
+        model = LinearRegression()
+        model.fit(X, y)
+        
+        st.subheader("Enter values for prediction")
+        pred_values = [st.number_input(f"Value for {feature}", value=0.0) for feature in data_name]
+        prediction = model.predict(pd.DataFrame([pred_values], columns=data_name))
+
+        st.write("Prediction:", prediction[0])
+else:
+    st.error("File not loaded")