Spaces:
Build error
Build error
File size: 7,633 Bytes
6607e79 7abab37 6607e79 7abab37 6607e79 900c0ad 6607e79 71227fd 6607e79 71227fd 7abab37 6607e79 7abab37 71227fd 6607e79 900c0ad cc89531 f076a08 7abab37 71227fd cc89531 71227fd f076a08 cc89531 6607e79 eacbd49 6607e79 eacbd49 6607e79 7abab37 900c0ad cc89531 6607e79 92a085a 6607e79 f076a08 6607e79 f076a08 7abab37 1a09a89 7abab37 1a09a89 6607e79 7abab37 92a085a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 |
import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from io import StringIO
import openpyxl
import matplotlib.font_manager as fm
from scipy import stats
# νκΈ ν°νΈ μ€μ
def set_font():
font_path = "Pretendard-Bold.ttf" # μ€μ ν°νΈ νμΌ κ²½λ‘λ‘ λ³κ²½ν΄μ£ΌμΈμ
fm.fontManager.addfont(font_path)
return {'font.family': 'Pretendard-Bold', 'axes.unicode_minus': False}
# ν°νΈ μ€μ μ κ°μ Έμ΅λλ€
font_settings = set_font()
# μΈμ
μν μ΄κΈ°ν
def init_session_state():
if 'data' not in st.session_state:
st.session_state.data = None
if 'processed_data' not in st.session_state:
st.session_state.processed_data = None
if 'numeric_columns' not in st.session_state:
st.session_state.numeric_columns = []
if 'categorical_columns' not in st.session_state:
st.session_state.categorical_columns = []
if 'x_var' not in st.session_state:
st.session_state.x_var = None
if 'y_var' not in st.session_state:
st.session_state.y_var = None
if 'slicers' not in st.session_state:
st.session_state.slicers = {}
# λ°μ΄ν° λ‘λ
@st.cache_data
def load_data(file):
file_extension = file.name.split('.')[-1].lower()
if file_extension == 'csv':
data = pd.read_csv(file)
elif file_extension in ['xls', 'xlsx']:
data = pd.read_excel(file)
else:
st.error("μ§μλμ§ μλ νμΌ νμμ
λλ€. CSV, XLS, λλ XLSX νμΌμ μ
λ‘λν΄μ£ΌμΈμ.")
return None
return data
def manual_data_entry():
st.subheader("μλ λ°μ΄ν° μ
λ ₯")
col_names = st.text_input("μ΄ μ΄λ¦μ μΌνλ‘ κ΅¬λΆνμ¬ μ
λ ₯νμΈμ:").split(',')
col_names = [name.strip() for name in col_names if name.strip()]
if col_names:
num_rows = st.number_input("μ΄κΈ° νμ μλ₯Ό μ
λ ₯νμΈμ:", min_value=1, value=5)
data = pd.DataFrame(columns=col_names, index=range(num_rows))
edited_data = st.data_editor(data, num_rows="dynamic")
return edited_data
return None
def preprocess_data(data):
st.subheader("λ°μ΄ν° μ μ²λ¦¬")
# κ²°μΈ‘μΉ μ²λ¦¬
if data.isnull().sum().sum() > 0:
st.write("κ²°μΈ‘μΉ μ²λ¦¬:")
for column in data.columns:
if data[column].isnull().sum() > 0:
method = st.selectbox(f"{column} μ΄μ μ²λ¦¬ λ°©λ² μ ν:",
["μ κ±°", "νκ· μΌλ‘ λ체", "μ€μκ°μΌλ‘ λ체", "μ΅λΉκ°μΌλ‘ λ체"])
if method == "μ κ±°":
data = data.dropna(subset=[column])
elif method == "νκ· μΌλ‘ λ체":
data[column].fillna(data[column].mean(), inplace=True)
elif method == "μ€μκ°μΌλ‘ λ체":
data[column].fillna(data[column].median(), inplace=True)
elif method == "μ΅λΉκ°μΌλ‘ λ체":
data[column].fillna(data[column].mode()[0], inplace=True)
# λ°μ΄ν° νμ
λ³ν
for column in data.columns:
if data[column].dtype == 'object':
try:
data[column] = pd.to_numeric(data[column])
st.write(f"{column} μ΄μ μ«μνμΌλ‘ λ³ννμ΅λλ€.")
except ValueError:
st.write(f"{column} μ΄μ λ²μ£ΌνμΌλ‘ μ μ§λ©λλ€.")
# μ«μν μ΄κ³Ό λ²μ£Όν μ΄ λΆλ¦¬
st.session_state.numeric_columns = data.select_dtypes(include=['float64', 'int64']).columns.tolist()
st.session_state.categorical_columns = data.select_dtypes(include=['object']).columns.tolist()
return data
def create_slicers(data):
for col in st.session_state.categorical_columns:
if data[col].nunique() <= 10: # κ³ μ κ°μ΄ 10κ° μ΄νμΈ κ²½μ°μλ§ μ¬λΌμ΄μ μμ±
st.session_state.slicers[col] = st.multiselect(
f"{col} μ ν",
options=sorted(data[col].unique()),
default=sorted(data[col].unique())
)
def apply_slicers(data):
for col, selected_values in st.session_state.slicers.items():
if selected_values:
data = data[data[col].isin(selected_values)]
return data
def plot_correlation_heatmap(data):
corr = data[st.session_state.numeric_columns].corr()
fig = px.imshow(corr, color_continuous_scale='RdBu_r', zmin=-1, zmax=1)
fig.update_layout(title='μκ΄κ΄κ³ ννΈλ§΅')
st.plotly_chart(fig)
def plot_scatter_with_regression(data, x_var, y_var):
fig = px.scatter(data, x=x_var, y=y_var, color='λ°' if 'λ°' in data.columns else None)
# νκ·μ μΆκ°
x = data[x_var]
y = data[y_var]
slope, intercept, r_value, p_value, std_err = stats.linregress(x, y)
line_x = np.array([x.min(), x.max()])
line_y = slope * line_x + intercept
fig.add_trace(go.Scatter(x=line_x, y=line_y, mode='lines', name='νκ·μ '))
r_squared = r_value ** 2
fig.update_layout(
title=f'{x_var}μ {y_var}μ κ΄κ³ (R-squared: {r_squared:.4f})',
xaxis_title=x_var,
yaxis_title=y_var,
annotations=[
dict(
x=0.5,
y=1.05,
xref='paper',
yref='paper',
text=f'R-squared: {r_squared:.4f}',
showarrow=False,
)
]
)
st.plotly_chart(fig)
# μΆκ° ν΅κ³ μ 보
st.write(f"μκ΄κ³μ: {r_value:.4f}")
st.write(f"p-value: {p_value:.4f}")
st.write(f"νμ€ μ€μ°¨: {std_err:.4f}")
def perform_analysis(data):
st.header("νμμ λ°μ΄ν° λΆμ")
# μ¬λΌμ΄μ μμ± λ° μ μ©
create_slicers(data)
filtered_data = apply_slicers(data)
# μμ½ ν΅κ³
st.write("μμ½ ν΅κ³:")
st.write(filtered_data.describe())
# μκ΄κ΄κ³ ννΈλ§΅
st.subheader("μκ΄κ΄κ³ ννΈλ§΅")
plot_correlation_heatmap(filtered_data)
# μ¬μ©μκ° μ νν λ λ³μμ λν μ°μ λ λ° νκ· λΆμ
st.subheader("λ λ³μ κ°μ κ΄κ³ λΆμ")
x_var = st.selectbox("XμΆ λ³μ μ ν", options=st.session_state.numeric_columns, key='x_var')
y_var = st.selectbox("YμΆ λ³μ μ ν", options=[col for col in st.session_state.numeric_columns if col != x_var], key='y_var')
if x_var and y_var:
plot_scatter_with_regression(filtered_data, x_var, y_var)
def main():
st.title("μΈν°λν°λΈ EDA ν΄ν·")
init_session_state()
data_input_method = st.radio("λ°μ΄ν° μ
λ ₯ λ°©λ² μ ν:", ("νμΌ μ
λ‘λ", "μλ μ
λ ₯"))
if data_input_method == "νμΌ μ
λ‘λ":
uploaded_file = st.file_uploader("CSV, XLS, λλ XLSX νμΌμ μ ννμΈμ", type=["csv", "xls", "xlsx"])
if uploaded_file is not None:
st.session_state.data = load_data(uploaded_file)
else:
st.session_state.data = None
else:
st.session_state.data = manual_data_entry()
if st.session_state.data is not None:
st.subheader("λ°μ΄ν° 미리보기 λ° μμ ")
st.write("λ°μ΄ν°λ₯Ό νμΈνκ³ νμν κ²½μ° μμ νμΈμ:")
edited_data = st.data_editor(st.session_state.data, num_rows="dynamic")
if st.button("λ°μ΄ν° λΆμ μμ"):
st.session_state.processed_data = preprocess_data(edited_data)
perform_analysis(st.session_state.processed_data)
if __name__ == "__main__":
main() |