From 220adaf33aa1a24a887671146af4b6292cc5752a Mon Sep 17 00:00:00 2001
From: Karen Zeng <karen.zeng@outlook.com>
Date: Fri, 19 May 2023 15:32:02 -0400
Subject: [PATCH] Created a new dataframe to store all keys data

---
 View_h5_file.py | 56 +++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 52 insertions(+), 4 deletions(-)

diff --git a/View_h5_file.py b/View_h5_file.py
index da8d19e..4817c70 100644
--- a/View_h5_file.py
+++ b/View_h5_file.py
@@ -7,19 +7,67 @@ f = h5py.File('product1.h5','r')
 list(f.keys())
 for key in f.keys():
     print(f[key])
+    df = pd.read_hdf('product1.h5', key='df')
+    df = df._append(pd.read_hdf('product1.h5', key))
     # print(f[key].shape)
     # print(f[key].value)
-df = pd.read_hdf('product1.h5', key='df8')
+# df = pd.read_hdf('product1.h5', key='df7')
 print(df)
+'''
+# Open the HDF5 file
+with h5py.File('product1.h5', 'r') as file:
+    dataframes=pd.DataFrame(columns=['Product ID', 'Zip Code', 'Shown Price', 'Minimum Quantity', 'Total Price', 'Unit Price','Sales Count','Sold Status'])  
+    for key in file.keys():
+        # Read the dataframe from the HDF5 file
+        dataframe = pd.read_hdf('product1.h5', key)
 
+        # Append the dataframe to the list
+        dataframes._append(dataframe)
+
+# Print the number of dataframes read from the HDF5 file
+print(f"Read {len(dataframes)} dataframes from the HDF5 file")
+
+item_std_devs = {}
+for dataframe in dataframes:
+    item_name = dataframe['Product ID'].iloc[0]
+    std_dev = np.std(dataframe['Unit Price'])
+    item_std_devs[item_name] = std_dev
+
+# Print the item names and their corresponding standard deviations
+for item_name, std_dev in item_std_devs.items():
+    print(f"Item: {item_name}, Std Dev: {std_dev}")
+
+# Prepare the data for the graph
+x = list(item_std_devs.keys())
+y = list(item_std_devs.values())
+
+# Create a bar graph
+fig = go.Figure(data=[go.Bar(x=x, y=y)])
+
+# Customize the graph
+fig.update_layout(
+    title="Standard Deviation of Pricing for Each Item",
+    xaxis_title="Item",
+    yaxis_title="Standard Deviation",
+)
+
+# Save the graph as an HTML file
+report_file = 'test2.html'
+fig.write_html(report_file)
+
+
+
+'''
 # Calculate the standard deviation using pandas' function
-std_dev_unit = df.groupby('Zip Code')['Unit Price'].std()
+std_dev_unit = df.groupby('Product ID')['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')
+fig.update_layout(title='Standard Deviation of the Unit Pricing by Item', xaxis_title='Product ID', yaxis_title='Standard Deviation')
 
-report_file = 'test.html'
+report_file = 'test2.html'
 fig.write_html(report_file)
+
+