Spaces:
Sleeping
Sleeping
File size: 5,975 Bytes
d0c886e |
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 |
import pandas as pd
import plotly.express as px
import streamlit as st
# Configuring the Streamlit App:
st.set_page_config(
page_title='MAK Analytics Portal',
page_icon='📊'
)
# Adding Titles and Subtitles:
st.title(':rainbow[Data Analytics Portal]')
st.subheader(':gray[Explore Data with ease.]',divider='rainbow')
# File Upload Feature:
file = st.file_uploader('Drop csv,tsv or excel file', type=['csv', 'xlsx','tsv'])
if file:
if file.name.endswith('csv'):
data = pd.read_csv(file)
elif file.name.endswith('tsv'):
data=pd.read_tsv(file)
else:
data = pd.read_excel(file)
st.dataframe(data)
st.info('File is successfully Uploaded', icon='✔️')
# Exploring Basic Information:
st.subheader(':rainbow[Basic information of the dataset]',divider='rainbow')
tab1, tab2, tab3, tab4 = st.tabs(['Summary', 'Top and Bottom Rows', 'Data Types', 'Columns'])
with tab1:
st.write(f'There are {data.shape[0]} rows in dataset and {data.shape[1]} columns in the dataset')
st.subheader(':gray[Statistical summary of the dataset]')
st.dataframe(data.describe())
with tab2:
st.subheader(':gray[Top Rows]')
toprows = st.slider('Number of rows you want', 1, data.shape[0], key='topslider')
st.dataframe(data.head(toprows))
st.subheader(':gray[Bottom Rows]')
bottomrows = st.slider('Number of rows you want', 1, data.shape[0], key='bottomslider')
st.dataframe(data.tail(bottomrows))
with tab3:
st.subheader(':grey[Data types of column]')
st.dataframe(data.dtypes)
with tab4:
st.subheader('Column Names in Dataset')
st.write(list(data.columns))
# Column Value Counts:
st.subheader(':rainbow[Column Values To Count]',divider='rainbow')
with st.expander('Value Count'):
col1, col2 = st.columns(2)
with col1:
column = st.selectbox('Choose Column name', options=list(data.columns))
with col2:
toprows = st.number_input('Top rows', min_value=1, step=1)
count = st.button('Count')
if count:
result = data[column].value_counts().reset_index().head(toprows)
st.dataframe(result)
st.subheader('Visualization', divider='gray')
fig = px.bar(data_frame=result, x=column, y='count', text='count', template='plotly_white')
st.plotly_chart(fig)
fig = px.line(data_frame=result, x=column, y='count', text='count', template='plotly_white')
st.plotly_chart(fig)
fig = px.pie(data_frame=result, names=column, values='count')
st.plotly_chart(fig)
# Grouping Data for Deeper Insights:
st.subheader(':rainbow[Groupby : Simplify your data analysis]', divider='rainbow')
st.write('The groupby lets you summarize data by specific categories and groups')
with st.expander('Group By your columns'):
col1, col2, col3 = st.columns(3)
with col1:
groupby_cols = st.multiselect('Choose your column to groupby', options=list(data.columns))
with col2:
operation_col = st.selectbox('Choose column for operation', options=list(data.columns))
with col3:
operation = st.selectbox('Choose operation', options=['sum', 'max', 'min', 'mean', 'median', 'count'])
if groupby_cols:
result = data.groupby(groupby_cols).agg(
ans=(operation_col, operation)
).reset_index()
st.dataframe(result)
st.subheader(':gray[Data Visualization]', divider='gray')
graphs = st.selectbox('Choose your graphs', options=['line', 'bar', 'scatter', 'pie', 'sunburst'])
if graphs == 'line':
x_axis = st.selectbox('Choose X axis', options=list(result.columns))
y_axis = st.selectbox('Choose Y axis', options=list(result.columns))
color = st.selectbox('Color Information', options=[None] + list(result.columns))
fig = px.line(data_frame=result, x=x_axis, y=y_axis, color=color, markers='o')
st.plotly_chart(fig)
elif graphs == 'bar':
x_axis = st.selectbox('Choose X axis', options=list(result.columns))
y_axis = st.selectbox('Choose Y axis', options=list(result.columns))
color = st.selectbox('Color Information', options=[None] + list(result.columns))
facet_col = st.selectbox('Column Information', options=[None] + list(result.columns))
fig = px.bar(data_frame=result, x=x_axis, y=y_axis, color=color, facet_col=facet_col, barmode='group')
st.plotly_chart(fig)
elif graphs == 'scatter':
x_axis = st.selectbox('Choose X axis', options=list(result.columns))
y_axis = st.selectbox('Choose Y axis', options=list(result.columns))
color = st.selectbox('Color Information', options=[None] + list(result.columns))
size = st.selectbox('Size Column', options=[None] + list(result.columns))
fig = px.scatter(data_frame=result, x=x_axis, y=y_axis, color=color, size=size)
st.plotly_chart(fig)
elif graphs == 'pie':
values = st.selectbox('Choose Numerical Values', options=list(result.columns))
names = st.selectbox('Choose labels', options=list(result.columns))
fig = px.pie(data_frame=result, values=values, names=names)
st.plotly_chart(fig)
elif graphs == 'sunburst':
path = st.multiselect('Choose your Path', options=list(result.columns))
fig = px.sunburst(data_frame=result, path=path, values='ans')
st.plotly_chart(fig)
|