File size: 1,263 Bytes
a28390b
 
 
 
 
 
 
 
a109b1b
a28390b
 
 
 
 
 
 
 
 
84a7db7
a28390b
 
84a7db7
a28390b
 
 
 
 
 
 
 
 
 
 
 
89f34cc
a28390b
 
 
89f34cc
a28390b
 
 
 
 
 
89f34cc
a28390b
 
 
 
 
 
 
 
 
 
 
 
 
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
import streamlit as st
import pandas as pd

st.set_page_config(page_title="Datasets Preparation", page_icon="šŸ‘‹", layout="wide")

##########################################

# Read lines from the text file
with open("datafiles/sample_nep_corpus.txt") as file:
    items = file.readlines()

# Split each line into separate columns
datacorpus = pd.DataFrame(items, columns=["Content"])
# datacorpus.columns =["Content"]


# st.write(f"{datacorpus}")

datasentences = pd.read_csv("datafiles/sample_nep_sentences.csv")

data100k = pd.read_csv(
    r"datafiles/sample_nep_spell_100k.csv",
    nrows=50,
)


###########################################


st.title("Dataset Preparation")

st.write("---")
st.header(
    """
A Large Scale Nepali Text Corpus 
"""
)

st.caption("**Table 1.** A Large Scale Nepali Text Corpus")

st.dataframe(datacorpus, use_container_width=True)

st.write("---")
st.header(
    """
Sentence extracted from A Large Scale Nepali Text Corpus
"""
)
st.caption("**Table 2.** Extracted sentences")
st.dataframe(datasentences, use_container_width=True)

st.write("---")
st.header(
    """
Parallel dataset using extracted sentences
"""
)
st.caption("**Table 3.** 100k Dataset used for training")
st.dataframe(data100k, use_container_width=True)