Compare commits
15 Commits
987e255dad
...
c8cf0fe045
Author | SHA1 | Date |
---|---|---|
|
c8cf0fe045 | 1 year ago |
|
4d82767c68 | 1 year ago |
|
9cb0d90eb1 | 1 year ago |
|
3eac3f6b8d | 1 year ago |
|
c87308cc21 | 1 year ago |
|
d4aeb87f75 | 1 year ago |
|
3c5f6849f8 | 1 year ago |
|
cd0c85ea44 | 1 year ago |
|
96d390c749 | 1 year ago |
|
089cc66042 | 1 year ago |
|
2d1c867bed | 1 year ago |
|
a914c3f8f9 | 1 year ago |
|
70641ebca4 | 1 year ago |
|
e5f05a2c8a | 1 year ago |
|
972fde561f | 1 year ago |
@ -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/*
|
@ -1 +1,2 @@
|
|||||||
__pycache__
|
__pycache__
|
||||||
|
.venv
|
||||||
|
@ -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"]
|
@ -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
|
@ -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")
|
@ -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")
|
@ -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
|
Loading…
Reference in new issue