Update app.py
Browse files
app.py
CHANGED
@@ -36,7 +36,6 @@ def load_and_clean_data():
|
|
36 |
|
37 |
df = load_and_clean_data()
|
38 |
|
39 |
-
|
40 |
# Page navigation setup
|
41 |
page_names = ["Dashboard for GESI Conversation in Sri Lanka", "GESI Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"]
|
42 |
page = st.sidebar.selectbox("Choose a page", page_names)
|
@@ -63,49 +62,49 @@ color_palette = px.colors.sequential.Viridis
|
|
63 |
|
64 |
# Function to render the model prediction visualization page
|
65 |
def render_prediction_page():
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
# User input text area
|
72 |
-
user_input = st.text_are("Enter Text/Content here to analyze", height=150)
|
73 |
-
|
74 |
-
if st.button("Perfrom contextual Analysis"):
|
75 |
-
# Use run_pipeline to get predictions
|
76 |
-
predictions = run_pipeline(user_input)
|
77 |
-
|
78 |
-
# Extract prediction details
|
79 |
-
domain_label = prediction.get("domain_label", "Unknown")
|
80 |
-
domain_score = prediction.get("domain_socre", 0)
|
81 |
-
discrimination_label = prediction.get("discrimination_label", "Unknown")
|
82 |
-
discrimination_score = prediction.get("discrimination_score", 0)
|
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 |
def create_pie_chart(df, column, title):
|
110 |
fig = px.pie(df, names=column, title=title, hole=0.35)
|
111 |
fig.update_layout(margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1), font=dict(size=12))
|
@@ -132,16 +131,15 @@ def create_sentiment_distribution_chart(df):
|
|
132 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=10))
|
133 |
return fig
|
134 |
|
135 |
-
|
136 |
# Visualization for Correlation between Sentiment and Discrimination
|
137 |
def create_sentiment_discrimination_grouped_chart(df):
|
138 |
# Creating a crosstab of 'Sentiment' and 'Discrimination'
|
139 |
crosstab_df = pd.crosstab(df['Sentiment'], df['Discrimination'])
|
140 |
|
141 |
-
# Check if '
|
142 |
value_vars = crosstab_df.columns.intersection(['Discriminative', 'Non Discriminative']).tolist()
|
143 |
|
144 |
-
# If '
|
145 |
melted_df = pd.melt(crosstab_df.reset_index(), id_vars='Sentiment', value_vars=value_vars, var_name='Discrimination', value_name='Count')
|
146 |
|
147 |
# Proceeding to plot only if we have data to plot
|
@@ -152,8 +150,6 @@ def create_sentiment_discrimination_grouped_chart(df):
|
|
152 |
else:
|
153 |
return "No data to display for the selected filters."
|
154 |
|
155 |
-
|
156 |
-
|
157 |
# Function for Top Domains with Negative Sentiment Chart
|
158 |
def create_top_negative_sentiment_domains_chart(df):
|
159 |
domain_counts = df.groupby(['Domain', 'Sentiment']).size().unstack(fill_value=0)
|
@@ -164,7 +160,7 @@ def create_top_negative_sentiment_domains_chart(df):
|
|
164 |
colors = ['limegreen', 'crimson', 'darkcyan']
|
165 |
fig = px.bar(domain_counts_subset, x='Count', y='Domain', title='Top Domains with Negative Sentiment', color='Domain',
|
166 |
orientation='h', color_discrete_sequence=colors)
|
167 |
-
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Negative
|
168 |
return fig
|
169 |
|
170 |
# Function for Key Phrases in Negative Sentiment Content Chart
|
@@ -174,7 +170,7 @@ def create_key_phrases_negative_sentiment_chart(df):
|
|
174 |
count_values = trigrams.toarray().sum(axis=0)
|
175 |
ngram_freq = pd.DataFrame(sorted([(count_values[i], k) for k, i in cv.vocabulary_.items()], reverse=True))
|
176 |
ngram_freq.columns = ['frequency', 'ngram']
|
177 |
-
fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key
|
178 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
|
179 |
return fig
|
180 |
|
@@ -195,14 +191,13 @@ def create_key_phrases_positive_sentiment_chart(df):
|
|
195 |
ngram_freq.columns = ['frequency', 'ngram']
|
196 |
|
197 |
# Create the bar chart
|
198 |
-
fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key
|
199 |
|
200 |
# Update layout settings
|
201 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
|
202 |
|
203 |
return fig
|
204 |
|
205 |
-
|
206 |
# Function for Prevalence of Discriminatory Content Chart
|
207 |
def create_prevalence_discriminatory_content_chart(df):
|
208 |
domain_counts = df.groupby(['Domain', 'Discrimination']).size().unstack(fill_value=0)
|
@@ -226,7 +221,7 @@ def create_top_discriminatory_domains_chart(df):
|
|
226 |
def create_sentiment_distribution_by_channel_chart(df):
|
227 |
sentiment_by_channel = df.groupby(['Channel', 'Sentiment']).size().reset_index(name='counts')
|
228 |
color_map = {'Positive': 'blue', 'Neutral': 'lightblue', 'Negative': 'red'}
|
229 |
-
fig = px.bar(sentiment_by_channel, x='Channel', y='counts', color='Sentiment', title="Sentiment Distribution by Channel", barmode='group',
|
230 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Channel", yaxis_title="Counts", font=dict(size=10), title_x=0.5)
|
231 |
return fig
|
232 |
|
@@ -237,13 +232,12 @@ def create_channel_discrimination_chart(df):
|
|
237 |
fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=20, r=20, t=50, b=20), font=dict(size=10), title_x=0.5)
|
238 |
return fig
|
239 |
|
240 |
-
|
241 |
# Function for rendering dashboard
|
242 |
def render_dashboard(page, df_filtered):
|
243 |
if page == "Dashboard for GESI Conversations in Sri Lanka":
|
244 |
render_prediction_page()
|
245 |
elif page == "GESI Overview":
|
246 |
-
st.title("
|
247 |
col1, col2 = st.columns(2)
|
248 |
with col1:
|
249 |
st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
|
@@ -290,6 +284,5 @@ def render_dashboard(page, df_filtered):
|
|
290 |
with col2:
|
291 |
st.plotly_chart(create_channel_discrimination_chart(df_filtered))
|
292 |
|
293 |
-
|
294 |
# Render the selected dashboard page
|
295 |
render_dashboard(page, df_filtered)
|
|
|
36 |
|
37 |
df = load_and_clean_data()
|
38 |
|
|
|
39 |
# Page navigation setup
|
40 |
page_names = ["Dashboard for GESI Conversation in Sri Lanka", "GESI Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"]
|
41 |
page = st.sidebar.selectbox("Choose a page", page_names)
|
|
|
62 |
|
63 |
# Function to render the model prediction visualization page
|
64 |
def render_prediction_page():
|
65 |
+
st.title("Dashboard for GESI Conversations in Sri Lanka")
|
66 |
+
st.write("""
|
67 |
+
Instant Analysis: Enter any text snippet and get immediate predictions from our model trained on English, Sinhala, and Tamil languages.\n\n
|
68 |
+
Domain Identification: Discover the subject matter of your text with a quantifiable domain score.
|
69 |
+
""")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
+
# User input text area
|
72 |
+
user_input = st.text_area("Enter Text/Content here to analyze", height=150)
|
73 |
|
74 |
+
if st.button("Perform Contextual Analysis"):
|
75 |
+
# Use run_pipeline to get predictions
|
76 |
+
predictions = run_pipeline(user_input)
|
77 |
+
|
78 |
+
# Extract prediction details
|
79 |
+
domain_label = predictions.get("domain_label", "Unknown")
|
80 |
+
domain_score = predictions.get("domain_score", 0)
|
81 |
+
discrimination_label = predictions.get("discrimination_label", "Unknown")
|
82 |
+
discrimination_score = predictions.get("discrimination_score", 0)
|
83 |
+
|
84 |
+
# Visualization layout
|
85 |
+
col1, col2 = st.columns(2)
|
86 |
+
|
87 |
+
with col1:
|
88 |
+
st.markdown("#### Domain Label")
|
89 |
+
st.markdown(f"## {domain_label}")
|
90 |
+
st.progress(domain_score)
|
91 |
+
|
92 |
+
with col2:
|
93 |
+
st.markdown("#### Discrimination Label")
|
94 |
+
st.markdown(f"## {discrimination_label}")
|
95 |
+
st.progress(discrimination_score)
|
96 |
+
|
97 |
+
col3, col4 = st.columns(2)
|
98 |
+
|
99 |
+
with col3:
|
100 |
+
# Display Domain Score in Bold
|
101 |
+
st.markdown(f'**Domain Score: {domain_score:.2f}**', unsafe_allow_html=True)
|
102 |
+
|
103 |
+
with col4:
|
104 |
+
# Display Discrimination Score in Bold
|
105 |
+
st.markdown(f'**Discrimination Score: {discrimination_score:.2f}**', unsafe_allow_html=True)
|
106 |
+
|
107 |
+
# Visualization for Domain Distribution
|
108 |
def create_pie_chart(df, column, title):
|
109 |
fig = px.pie(df, names=column, title=title, hole=0.35)
|
110 |
fig.update_layout(margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1), font=dict(size=12))
|
|
|
131 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=10))
|
132 |
return fig
|
133 |
|
|
|
134 |
# Visualization for Correlation between Sentiment and Discrimination
|
135 |
def create_sentiment_discrimination_grouped_chart(df):
|
136 |
# Creating a crosstab of 'Sentiment' and 'Discrimination'
|
137 |
crosstab_df = pd.crosstab(df['Sentiment'], df['Discrimination'])
|
138 |
|
139 |
+
# Check if 'Discriminative' and 'Non Discriminative' are in the columns after the crosstab operation
|
140 |
value_vars = crosstab_df.columns.intersection(['Discriminative', 'Non Discriminative']).tolist()
|
141 |
|
142 |
+
# If 'Non Discriminative' is not in columns, it will not be included in melting
|
143 |
melted_df = pd.melt(crosstab_df.reset_index(), id_vars='Sentiment', value_vars=value_vars, var_name='Discrimination', value_name='Count')
|
144 |
|
145 |
# Proceeding to plot only if we have data to plot
|
|
|
150 |
else:
|
151 |
return "No data to display for the selected filters."
|
152 |
|
|
|
|
|
153 |
# Function for Top Domains with Negative Sentiment Chart
|
154 |
def create_top_negative_sentiment_domains_chart(df):
|
155 |
domain_counts = df.groupby(['Domain', 'Sentiment']).size().unstack(fill_value=0)
|
|
|
160 |
colors = ['limegreen', 'crimson', 'darkcyan']
|
161 |
fig = px.bar(domain_counts_subset, x='Count', y='Domain', title='Top Domains with Negative Sentiment', color='Domain',
|
162 |
orientation='h', color_discrete_sequence=colors)
|
163 |
+
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Negative Sentiment Content Count", yaxis_title="Domain", font=dict(size=10))
|
164 |
return fig
|
165 |
|
166 |
# Function for Key Phrases in Negative Sentiment Content Chart
|
|
|
170 |
count_values = trigrams.toarray().sum(axis=0)
|
171 |
ngram_freq = pd.DataFrame(sorted([(count_values[i], k) for k, i in cv.vocabulary_.items()], reverse=True))
|
172 |
ngram_freq.columns = ['frequency', 'ngram']
|
173 |
+
fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key Phrases in Negative Sentiment Content')
|
174 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
|
175 |
return fig
|
176 |
|
|
|
191 |
ngram_freq.columns = ['frequency', 'ngram']
|
192 |
|
193 |
# Create the bar chart
|
194 |
+
fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key Phrases in Positive Sentiment Content')
|
195 |
|
196 |
# Update layout settings
|
197 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
|
198 |
|
199 |
return fig
|
200 |
|
|
|
201 |
# Function for Prevalence of Discriminatory Content Chart
|
202 |
def create_prevalence_discriminatory_content_chart(df):
|
203 |
domain_counts = df.groupby(['Domain', 'Discrimination']).size().unstack(fill_value=0)
|
|
|
221 |
def create_sentiment_distribution_by_channel_chart(df):
|
222 |
sentiment_by_channel = df.groupby(['Channel', 'Sentiment']).size().reset_index(name='counts')
|
223 |
color_map = {'Positive': 'blue', 'Neutral': 'lightblue', 'Negative': 'red'}
|
224 |
+
fig = px.bar(sentiment_by_channel, x='Channel', y='counts', color='Sentiment', title="Sentiment Distribution by Channel", barmode='group', color_discrete_map=color_map)
|
225 |
fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Channel", yaxis_title="Counts", font=dict(size=10), title_x=0.5)
|
226 |
return fig
|
227 |
|
|
|
232 |
fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=20, r=20, t=50, b=20), font=dict(size=10), title_x=0.5)
|
233 |
return fig
|
234 |
|
|
|
235 |
# Function for rendering dashboard
|
236 |
def render_dashboard(page, df_filtered):
|
237 |
if page == "Dashboard for GESI Conversations in Sri Lanka":
|
238 |
render_prediction_page()
|
239 |
elif page == "GESI Overview":
|
240 |
+
st.title("GESI Overview Dashboard")
|
241 |
col1, col2 = st.columns(2)
|
242 |
with col1:
|
243 |
st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
|
|
|
284 |
with col2:
|
285 |
st.plotly_chart(create_channel_discrimination_chart(df_filtered))
|
286 |
|
|
|
287 |
# Render the selected dashboard page
|
288 |
render_dashboard(page, df_filtered)
|