You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
88 lines
3.0 KiB
88 lines
3.0 KiB
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
|
|
import matplotlib.pyplot as plt
|
|
|
|
|
|
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])
|
|
|
|
|
|
|
|
|
|
fig = plt.figure()
|
|
dataframe_sorted = pd.concat([X, y], axis=1).sort_values(by=data_name)
|
|
|
|
X = dataframe_sorted[data_name[0]]
|
|
y = dataframe_sorted[target_name]
|
|
|
|
prediction_array_y = [
|
|
model.predict(pd.DataFrame([[dataframe_sorted[data_name[0]].iloc[i]]], columns=data_name))[0]
|
|
for i in range(dataframe_sorted.shape[0])
|
|
]
|
|
|
|
plt.scatter(dataframe_sorted[data_name[0]], dataframe_sorted[target_name], color='b')
|
|
plt.scatter(dataframe_sorted[data_name[0]], prediction_array_y, color='r')
|
|
|
|
st.pyplot(fig)
|
|
|
|
|
|
else:
|
|
st.error("File not loaded")
|