2023-05-16 16:44:15 -04:00
|
|
|
import h5py
|
|
|
|
|
import pandas as pd
|
2023-05-17 15:01:04 -04:00
|
|
|
import numpy as np
|
|
|
|
|
import plotly.graph_objects as go
|
2023-05-16 16:44:15 -04:00
|
|
|
|
|
|
|
|
f = h5py.File('product1.h5','r')
|
|
|
|
|
list(f.keys())
|
|
|
|
|
for key in f.keys():
|
|
|
|
|
print(f[key])
|
|
|
|
|
# print(f[key].shape)
|
|
|
|
|
# print(f[key].value)
|
|
|
|
|
df = pd.read_hdf('product1.h5', key='df8')
|
|
|
|
|
print(df)
|
2023-05-17 15:01:04 -04:00
|
|
|
|
|
|
|
|
# Calculate the standard deviation using pandas' function
|
|
|
|
|
std_dev_unit = df.groupby('Zip Code')['Unit Price'].std()
|
|
|
|
|
std_dev_displayed = df.groupby('Zip Code')['Shown Price'].std()
|
|
|
|
|
|
|
|
|
|
# Generate the graph using Plotly
|
|
|
|
|
fig = go.Figure()
|
|
|
|
|
fig.add_trace(go.Bar(x=std_dev_unit.index, y=std_dev_unit.values))
|
|
|
|
|
fig.update_layout(title='Standard Deviation of the Unit Pricing by Item', xaxis_title='Zip Code', yaxis_title='Standard Deviation')
|
|
|
|
|
|
|
|
|
|
report_file = 'test.html'
|
|
|
|
|
fig.write_html(report_file)
|
