Update curated.py

curated.py

@@ -57,6 +57,638 @@ fig = px.treemap(treemap_data, path=['Category', 'Source'], values='Count', hove
 # Display treemap if you want to update the size.update_layout(width=800, height=600)
 treemap_chart = fig
 
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='group',
+    title='Wikipedia Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+wikipedia_bar = fig
+
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='group',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+freelaw_bar = fig
+
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
+data = {
+    'Filter': ['Downloaded Lines', 'Language Filter', 'Min Word Count', 'Unigram Log Probability'],
+    'Wikipedia': [61614907, 61614907, 60468491, 60468491],
+    'Freelaw': [75971288, 73690766, 68171834, 68123174],
+    'DM Maths': [112559888, 112559888, 112559888, 112559888],
+    'USPTO': [6880276, 6878964, 6749922, 6749389],
+    'PG19': [28752, 28683, 28682, 28632],
+    'Hackernews': [2064931, 2010802, 2010488, 2003636],
+    'Ubuntu IRC': [37966, 23501, 23468, 23205],
+    'Europarl': [69814, 69814, 69814, 69814],
+    'StackExchange': [23246548, 23246548, 23246352, 23246352],
+    'Arxiv': [1911867, 1869441, 1763840, 1762661],
+    'S2ORC': [12963563, 12963563, 12963563, 12963563],
+    'S2ORC Abstract': [102324176, 83867601, 82889293, 82777912],
+    'Pubmed Central': [5230932, 4830486, 4768310, 4767474],
+    'Pubmed Abstract': [25787474, 25784374, 25747955, 25746724],
+    'Phil Papers': [49389, 39175, 39175, 39128]
+}
+
+# Creating a dataframe
+df = pd.DataFrame(data)
+
+# Creating the stacked bar chart
+fig = go.Figure()
+
+# Add trace for each dataset
+for dataset in df.columns[1:]:
+    fig.add_trace(go.Bar(
+        name=dataset,
+        x=df['Filter'],
+        y=df[dataset]
+    ))
+
+# Update the layout
+fig.update_layout(
+    barmode='stack',
+    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    xaxis_title='Filter',
+    yaxis_title='Number of Lines',
+    legend_title='Dataset',
+    height=600,
+    width=1000
+)
+
+# Show the plot
+diff2_stacked_bar = fig
 
 
 filtering_process = Div(
@@ -65,6 +697,7 @@ filtering_process = Div(
     ),
     Section(
         H3("Wikipedia"),
+        wikipedia_bar,
         H4("Download and Extraction"),
         Ol(
             Li("Downloaded from Wikimedia official dump of wikipedia on huggingface https://huggingface.co/datasets/wikimedia/wikipedia/tree/main"),