File size: 2,693 Bytes
b523dd4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import pandas as pd
import streamlit as st

def transform_data(df):
    # Transform 'respond' variable
    respond_mapping = {
        "Parent": 1, "Teacher": 2, "Self": 3, "Other": 4, 
        "Significant other": 5, "Parent 1": 6, "Parent 2": 7, 
        "Not available": 999
    }
    if 'respond' in df:
        df['respond'] = df['respond'].map(respond_mapping)

    # Transform 'sri_ts' and 'sld_ts' variables
    sri_sld_values = {
    8: 36.6, 9: 42.1, 10: 44.8, 11: 46.8, 12: 48.5, 13: 50.0, 14: 51.3,
    15: 52.5, 16: 53.7, 17: 54.9, 18: 56.0, 19: 57.1, 20: 58.2, 21: 59.3,
    22: 60.3, 23: 61.4, 24: 62.4, 25: 63.5, 26: 64.5, 27: 65.6, 28: 66.6,
    29: 67.6, 30: 68.7, 31: 69.7, 32: 70.7, 33: 71.8, 34: 72.9, 35: 74.1,
    36: 75.4, 37: 76.8, 38: 78.5, 39: 80.3, 40: 82.7
    }

    if 'sri_rs' in df.columns:
        df['sri_ts'] = df['sri_rs'].map(sri_sld_values).fillna("NA")

    if 'sld_rs' in df.columns:
        df['sld_ts'] = df['sld_rs'].map(sri_sld_values).fillna("NA")

    # Transform 'dsm_cross_ch' variables
    dsm_cross_ch_cols = [f'dsm_cross_ch{num}' for num in range(20, 26)]
    for col in dsm_cross_ch_cols:
        if col in df:
            df[col] = df[col].map({0: 2, 1: 1})

    # Transform 'dsm_cross_pg' variables
    dsm_cross_pg_cols = [f'dsm_cross_pg{num}' for num in range(20, 26)]
    for col in dsm_cross_pg_cols:
        if col in df:
            df[col] = df[col].map({0: 1, 1: 2, 2: -9})

    # Transform 'rcads_y' variables
    rcads_y_cols = [f'rcads_y{num}' for num in range(14, 27)]
    for col in rcads_y_cols:
        if col in df:
            df[col] = df[col] + 1

    # Ensure rcads_y26 exists and set default values
    if 'rcads_y26' not in df:
        df['rcads_y26'] = 1

    # Return transformed dataframe
    return df

def main():
    st.title("Data Transformation App")

    uploaded_file = st.file_uploader("Upload CSV or Excel file", type=['csv', 'xlsx'])
    if uploaded_file:
        # Determine the file type and read data accordingly
        if uploaded_file.name.endswith('.csv'):
            df = pd.read_csv(uploaded_file)
        elif uploaded_file.name.endswith('.xlsx'):
            df = pd.read_excel(uploaded_file)

        # Transform the data
        transformed_df = transform_data(df)

        # Display transformed data
        st.write("Transformed Data:")
        st.dataframe(transformed_df)

        # Download link for transformed data
        st.download_button(
            label="Download Transformed Data",
            data=transformed_df.to_csv(index=False).encode('utf-8'),
            file_name='transformed_data.csv',
            mime='text/csv',
        )

if __name__ == '__main__':
    main()