delete np

Co-authored-by: bastien ollier <bastien.ollier@etu.uca.fr>
Co-authored-by: clfreville2 <clement.freville2@etu.uca.fr>
Reviewed-on: https://codefirst.iut.uca.fr/git/clement.freville2/miner/pulls/2
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>

frontend/exploration.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import streamlit as st
+
+st.set_page_config(
+    page_title="Project Miner",
+    layout="wide"
+)
+
+st.title("Home")
+
+### Exploration
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+if uploaded_file is not None:
+    st.session_state.data = pd.read_csv(uploaded_file)
+    st.success("File loaded successfully!")
+
+
+if "data" in st.session_state:
+    data = st.session_state.data
+    st.write(data.head(10))
+    st.write(data.tail(10))
+
+    st.header("Data Preview")
+    
+    st.subheader("First 5 Rows")
+    st.write(data.head())
+    
+    st.subheader("Last 5 Rows")
+    st.write(data.tail())
+    
+    st.header("Data Summary")
+    
+    st.subheader("Basic Information")
+    col1, col2 = st.columns(2)
+    col1.metric("Number of Rows", data.shape[0])
+    col2.metric("Number of Columns", data.shape[1])
+    
+    st.write(f"Column Names: {list(data.columns)}")
+    
+    st.subheader("Missing Values by Column")
+    missing_values = data.isnull().sum()
+    st.write(missing_values)
+    
+    st.subheader("Statistical Summary")
+    st.write(data.describe())
+    

frontend/main.py

@@ -1,64 +0,0 @@
-import pandas as pd
-import streamlit as st
-import matplotlib.pyplot as plt
-import seaborn as sns
-from pandas.api.types import is_numeric_dtype
-
-st.set_page_config(
-    page_title="Project Miner",
-    layout="wide"
-)
-
-### Exploration
-uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
-
-if uploaded_file:
-    data = pd.read_csv(uploaded_file)
-    st.success("File loaded successfully!")
-
-    st.header("Data Preview")
-    
-    st.subheader("First 5 Rows")
-    st.write(data.head())
-    
-    st.subheader("Last 5 Rows")
-    st.write(data.tail())
-    
-    st.header("Data Summary")
-    
-    st.subheader("Basic Information")
-    col1, col2 = st.columns(2)
-    col1.metric("Number of Rows", data.shape[0])
-    col2.metric("Number of Columns", data.shape[1])
-    
-    st.write(f"Column Names: {list(data.columns)}")
-    
-    st.subheader("Missing Values by Column")
-    missing_values = data.isnull().sum()
-    st.write(missing_values)
-    
-    st.subheader("Statistical Summary")
-    st.write(data.describe())
-    
-    ### Visualization
-
-    st.header("Data Visualization")
-
-    st.subheader("Histogram")
-    column_to_plot = st.selectbox("Select Column for Histogram", data.columns)
-    if column_to_plot:
-        fig, ax = plt.subplots()
-        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()
-        sns.boxplot(data=data, x=column_to_plot, ax=ax)
-        ax.set_title(f'Boxplot of {column_to_plot}')
-        st.pyplot(fig)

frontend/pages/clustering:_dbscan.py

@@ -0,0 +1,29 @@
+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=2)
+        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:
+        x = data[data_name].to_numpy()
+
+        dbscan = DBSCAN(eps=eps, min_samples=min_samples)
+        y_dbscan = dbscan.fit_predict(x)
+
+
+        fig, ax = plt.subplots(figsize=(12,8))
+        plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis")
+        st.pyplot(fig)
+
+else:
+    st.error("file not loaded")

frontend/pages/clustering:_kmeans.py

@@ -0,0 +1,36 @@
+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=2)
+        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:
+        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, ax = plt.subplots(figsize=(12,8))
+        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")
+        st.pyplot(fig)
+
+else:
+    st.error("file not loaded")

frontend/pages/visualization.py

@@ -0,0 +1,30 @@
+import streamlit as st
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+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()
+        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()
+        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")