Spaces:
Sleeping
Sleeping
File size: 5,155 Bytes
5c802bc |
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 |
import streamlit as st
import pandas as pd
import numpy as np
import io
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
import seaborn as sns
import base64
def preview_data():
if "data" in st.session_state:
data = st.session_state["data"]
st.write("### Dataset Preview Options:")
preview_option = st.radio(
"Select how to preview the dataset:",
options=["Head", "Tail", "Custom Number of Rows"],
index=0
)
if preview_option == "Head":
st.write("### First 5 Rows of the Dataset:")
st.dataframe(data.head())
elif preview_option == "Tail":
st.write("### Last 5 Rows of the Dataset:")
st.dataframe(data.tail())
elif preview_option == "Custom Number of Rows":
number = st.slider(
"Select Number of Rows to Display:", 1, len(data))
st.write(f"### First {number} Rows of the Dataset:")
st.dataframe(data.head(number))
# Show entire data
if st.checkbox("Show all data"):
st.write(data)
# Show column names
if st.checkbox("Show Column Names"):
st.write(data.columns)
# Show dataset dimensions (rows and columns)
if st.checkbox("Show Dimensions"):
st.write(data.shape)
else:
st.warning("Please upload a dataset to view options.")
def data_cleaning():
if "data" in st.session_state:
data = st.session_state["data"]
st.subheader("Data Cleaning")
col_option = st.selectbox("Choose your option", [
"Check all numeric features are numeric?", "Show unique values of categorical features"])
# Check and convert numeric columns
if col_option == "Check all numeric features are numeric?":
st.write("Converting all numeric columns to numeric types...")
numeric_columns = list(
data.select_dtypes(include=np.number).columns)
for col in numeric_columns:
data[col] = pd.to_numeric(data[col], errors='coerce')
st.write("Done!")
# Show unique values for categorical features
elif col_option == "Show unique values of categorical features":
st.write("Unique values for categorical features:")
for column in data.columns:
# check for categorical features (strings)
if data[column].dtype == object:
st.write(f"{column}: {data[column].unique()}")
st.write("====================================")
else:
st.warning("Please upload a dataset to perform data cleaning.")
def modify_column_names():
st.title("Modify Column Names")
# Ensure data exists in the session
if "data" in st.session_state:
df = st.session_state["data"]
st.write('### *Current Column Names*')
st.table(df.columns)
st.write('### *Modify Column Names*')
with st.expander("Modify Column Names", expanded=True):
before_col = st.session_state.get(
"modified_columns", list(df.columns))
before_col_df = pd.DataFrame(before_col, columns=['Column Name'])
st.table(before_col_df)
col3, col4, col5, col6 = st.columns(4)
if st.button('Convert to Uppercase'):
st.session_state.modified_columns = [
col.upper() for col in before_col]
if st.button('Convert to Lowercase'):
st.session_state.modified_columns = [
col.lower() for col in before_col]
if st.button('Replace Spaces with Underscore'):
st.session_state.modified_columns = [
col.replace(" ", "_") for col in before_col]
if st.button('Capitalize First Letters'):
st.session_state.modified_columns = [
col.title() for col in before_col]
df.columns = st.session_state.modified_columns
st.success("Changes applied successfully.")
st.table(pd.DataFrame(df.columns, columns=['Modified Columns']))
st.write("### *Modify a Specific Column Name*")
column_select = st.selectbox(
'Select column to modify', options=st.session_state.modified_columns)
new_column_name = st.text_input('Enter new column name')
if st.button('Update Column Name'):
if column_select and new_column_name:
st.session_state.modified_columns = [
new_column_name if col == column_select else col for col in st.session_state.modified_columns]
df.columns = st.session_state.modified_columns
st.success("Column name updated.")
st.table(pd.DataFrame(
df.columns, columns=['Modified Columns']))
else:
st.warning("Please upload a dataset first.")
|