Upload 6 files

app.py

@@ -0,0 +1,15 @@
+import streamlit as st
+import eda
+import prediction
+import home
+
+PAGES = {
+    "Home": home,
+    "Exploratory Data Analysis": eda,
+    "Prediction": prediction
+}
+st.sidebar.title('Navigation')
+
+selection = st.sidebar.selectbox("Go to", list(PAGES.keys()))
+page = PAGES[selection]
+page.app()

eda.py

@@ -0,0 +1,63 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import nltk
+nltk.download('stopwords')
+from nltk.corpus import stopwords
+from wordcloud import WordCloud
+
+def app():
+  df_original = pd.read_csv("data.csv", delimiter=";")
+  df = df_original.copy()
+  df.drop_duplicates(inplace=True)
+
+  temp_a = df.copy()
+  temp_a['text_length'] = temp_a['text'].apply(len)
+  st.header('Exploratory Data Analysis', divider='rainbow')
+  eda_list = ["Text Length Distribution", "Sentiment Distribution", "Word Clouds", "Boxplot Distributions"]
+  val = st.sidebar.radio("Choose plot to show", eda_list)
+  stop_words = set(stopwords.words('english'))
+  def plot_wordcloud(sentiment):
+    text = ' '.join(df[df['feeling'] == sentiment]['text'])
+    wordcloud = WordCloud(stopwords=stop_words, background_color='white').generate(text)
+    plt.figure(figsize=(10, 6))
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis('off')
+    plt.title(f"Word Cloud for {sentiment} Sentiment")
+    st.pyplot(plt)
+  if val == "Text Length Distribution":
+    # Plot distribution
+    st.header('Text Length Distribution')
+    plt.figure(figsize=(10, 6))
+    plt.hist(temp_a['text_length'], bins=30, color='skyblue')
+    plt.title('Text Length Distribution')
+    plt.xlabel('Text Length (characters)')
+    plt.ylabel('Frequency')
+    st.pyplot(plt)
+    st.write("Insight: the numerical values in our data are all normal distributions.")
+  elif val == "Sentiment Distribution":
+    sentiment_counts = df['feeling'].value_counts()
+    st.header('Sentiment Distribution')
+    # Plot pie chart
+    plt.figure(figsize=(8, 6))
+    plt.pie(sentiment_counts, labels=sentiment_counts.index, autopct='%1.1f%%', startangle=140, colors=sns.color_palette('viridis', len(sentiment_counts)))
+    plt.title('Sentiment Distribution')
+    plt.axis('equal')
+    st.pyplot(plt)
+    st.write("Insight: joy and sadness dominate the sentiment dataset, with joy taking the first place in 33.8%")
+
+    plt.figure(figsize=(8, 6))
+    sns.countplot(data=df, x='feeling', palette='viridis')
+    plt.title('Sentiment Distribution')
+    plt.xlabel('Sentiment')
+    plt.ylabel('Count')
+    st.pyplot(plt)
+    st.write("Insight: surprise sentiment has the lowest value of around 900 data")
+  elif val == "Word Clouds":
+    plot_wordcloud('joy')
+    plot_wordcloud('sadness')
+    plot_wordcloud('anger')
+    plot_wordcloud('love')
+    plot_wordcloud('surprise')
+    plot_wordcloud('fear')

home.py

@@ -0,0 +1,15 @@
+import streamlit as st
+
+def app():
+    st.header('Sentiment Analysis Project', divider='rainbow')
+    st.write("""
+    This deep learning project is designed to predict the feeling of a user's text. This can be helpful for 
+    companies, C-level executives and social media influencers to really understand what their users actually feel about
+    their products, posts, services, etc. 
+             
+    In addition, research shows that 70% of customer purchase decisions are based on emotional 
+    factors and only 30% on rational factors. By analyzing likes, comments, shares and mentions, brands can gain valuable insights into 
+    the emotional drivers that influence purchase decisions as well as brand loyalty.
+             
+    This means, that this technology can help companies and businesses make better and more strategical decisions.
+    """)

requirements.txt

@@ -2,3 +2,5 @@ pandas==2.2.2
 numpy==1.26.4
 tensorflow==2.15.1
 tensorflow_hub==0.16.1
+nltk==3.8.1
+WordCloud