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

@@ -130,6 +130,10 @@ class KNNStrategy(MVStrategy):
         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"
 

frontend/pages/normalization.py

@@ -16,9 +16,8 @@ if "data" in st.session_state:
             key=f"mv-{column}",
         )
         if isinstance(option, KNNStrategy):
-            print(option.available_features)
             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, value=option.n_neighbors, key=f"neighbors-{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")