analysis overview

Home.py

@@ -15,9 +15,9 @@ import streamlit as st
 # add_page_title()
 
 # Set page title
-st.set_page_config(page_title="Tiktok Analytics Dashboard", page_icon = "📊", layout = "centered", initial_sidebar_state = "auto")
+st.set_page_config(page_title="Enhanced TikTok Analytics Dashboard", page_icon = "📊", layout = "centered", initial_sidebar_state = "auto")
 
-st.header("Tiktok Analytics Dashboard")
+st.header("Enhanced TikTok Analytics Dashboard")
 
 
 

pages/04_Case Study:_Gaming_Clips.py

@@ -0,0 +1,279 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import datetime
+import plotly.express as px
+import plotly.graph_objects as go
+import statsmodels.api as sm
+from millify import millify
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import r2_score
+from st_aggrid import AgGrid
+import io
+import re
+import emoji
+from collections import Counter
+import openpyxl
+from gensim.models import Word2Vec
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.linear_model import LinearRegression
+from sklearn.ensemble import RandomForestRegressor
+from xgboost import XGBRegressor
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from sklearn.model_selection import train_test_split
+import seaborn as sns
+import matplotlib.pyplot as plt
+from mpl_toolkits.mplot3d import Axes3D
+
+
+# Set page title
+st.set_page_config(page_title="Case Study: Gaming Clips - Tiktok Analytics Dashboard", page_icon = "📊", layout = "centered", initial_sidebar_state = "auto")
+
+st.header("Case Study: Gaming Clips")
+
+selected_options = ["Background Information", "Uploaded Datasets", "Analysis"]
+selected = st.selectbox("Which section would you like to read?", options = selected_options)
+st.write("Current selection:", selected)
+if selected == "Background Information":
+    st.subheader("Background Information")
+elif selected == "Uploaded Datasets":
+    st.subheader("Uploaded Datasets")
+    last7days = pd.read_excel('gaming/Last 7 days.xlsx')
+    last28days = pd.read_excel('gaming/Last 28 days.xlsx')
+    last60days = pd.read_excel('gaming/Last 60 days.xlsx')
+    totalfollowers = pd.read_excel('gaming/Total followers.xlsx')
+    trendingvideos = pd.read_excel('gaming/Trending videos.xlsx')
+    videoposts = pd.read_excel('gaming/Video Posts.xlsx')
+
+    #function to convert any dataframe to a csv file
+    @st.cache_data
+
+    def convert_df(df):
+        # IMPORTANT: Cache the conversion to prevent computation on every rerun
+        return df.to_csv().encode('utf-8')
+
+    st.write('Last 7 days.xlsx')
+    st.write(last7days)
+    #converting the sample dataframe
+    csv = convert_df(last7days)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Last 7 days.csv',
+        mime='text/csv',
+    )
+
+    st.write('Last 28 days.xlsx')
+    st.write(last28days)
+    #converting the sample dataframe
+    csv = convert_df(last28days)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Last 28 days.csv',
+        mime='text/csv',
+    )
+
+    st.write('Last 60 days.xlsx')
+    st.write(last60days)
+    #converting the sample dataframe
+    csv = convert_df(last60days)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Last 60 days.csv',
+        mime='text/csv',
+    )
+
+    st.write('Total followers.xlsx')
+    st.write(totalfollowers)
+    #converting the sample dataframe
+    csv = convert_df(totalfollowers)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Total followers.csv',
+        mime='text/csv',
+    )
+
+    st.write('Trending videos.xlsx')
+    st.write(trendingvideos)
+    #converting the sample dataframe
+    csv = convert_df(trendingvideos)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Trending videos.csv',
+        mime='text/csv',
+    )
+
+    st.write('Video Posts.xlsx')
+    st.write(videoposts)
+    #converting the sample dataframe
+    csv = convert_df(videoposts)
+    #adding a download button to download csv file
+    st.download_button( 
+        label="Download data as CSV",
+        data=csv,
+        file_name='Video Posts.csv',
+        mime='text/csv',
+    )
+elif selected == "Analysis":
+    def plot_chart(data, chart_type, x_var, y_var, z_var=None, show_regression_line=False, show_r_squared=False):
+        scatter_marker_color = 'green'
+        regression_line_color = 'red'
+        if chart_type == "line":
+            fig = px.line(data, x=x_var, y=y_var)
+
+        elif chart_type == "bar":
+            fig = px.bar(data, x=x_var, y=y_var)
+
+        elif chart_type == "scatter":
+            fig = px.scatter(data, x=x_var, y=y_var, color_discrete_sequence=[scatter_marker_color])
+
+            if show_regression_line and x_var != 'Date':
+                X = data[x_var].values.reshape(-1, 1)
+                y = data[y_var].values.reshape(-1, 1)
+                model = LinearRegression().fit(X, y)
+                y_pred = model.predict(X)
+                r_squared = r2_score(y, y_pred)  # Calculate R-squared value
+
+                fig.add_trace(
+                    go.Scatter(x=data[x_var], y=y_pred[:, 0], mode='lines', name='Regression Line', line=dict(color=regression_line_color))
+                )
+
+                # Add R-squared value as a text annotation
+                fig.add_annotation(
+                    x=data[x_var].max(),
+                    y=y_pred[-1, 0],
+                    text=f"R-squared: {r_squared:.4f}",
+                    showarrow=False,
+                    font=dict(size=14),
+                    bgcolor='rgba(255, 255, 255, 0.8)',
+                    bordercolor='black',
+                    borderwidth=1,
+                    borderpad=4
+                )
+
+        elif chart_type == "heatmap":
+            fig = px.imshow(data, color_continuous_scale='Inferno')
+
+        elif chart_type == "scatter_3d":
+            if z_var is not None:
+                fig = px.scatter_3d(data, x=x_var, y=y_var, z=z_var, color=data.columns[0])
+            else:
+                st.warning("Please select Z variable for 3D line plot.")
+                return
+
+        elif chart_type == "line_3d":
+            if z_var is not None:
+                fig = go.Figure(data=[go.Scatter3d(x=data[x_var], y=data[y_var], z=data[z_var], mode='lines')])
+                fig.update_layout(scene=dict(xaxis_title=x_var, yaxis_title=y_var, zaxis_title=z_var))  # Set the axis name
+            else:
+                st.warning("Please select Z variable for 3D line plot.")
+                return
+
+        elif chart_type == "surface_3d":
+            if z_var is not None:
+                fig = go.Figure(data=[go.Surface(z=data.values)])
+                fig.update_layout(scene=dict(xaxis_title=x_var, yaxis_title=y_var, zaxis_title=z_var))  # Set the axis name
+            else:
+                st.warning("Please select Z variable for 3D line plot.")
+                return
+
+        elif chart_type == "radar":
+            fig = go.Figure()
+            for col in data.columns[1:]:
+                fig.add_trace(go.Scatterpolar(r=data[col], theta=data[x_var], mode='lines', name=col))
+            fig.update_layout(polar=dict(radialaxis=dict(visible=True, range=[data[data.columns[1:]].min().min(), data[data.columns[1:]].max().max()])))
+
+        st.plotly_chart(fig)
+
+    def plot_radar_chart(data, columns):
+        df = data[columns]
+        fig = go.Figure()
+
+        for i in range(len(df)):
+            date_label = data.loc[i, 'Date']
+            fig.add_trace(go.Scatterpolar(
+                r=df.loc[i].values,
+                theta=df.columns,
+                fill='toself',
+                name=date_label
+            ))
+
+        fig.update_layout(
+            polar=dict(
+                radialaxis=dict(
+                    visible=True,
+                    range=[0, df.max().max()]
+                )
+            ),
+            showlegend=True
+        )
+
+        st.plotly_chart(fig)
+    st.subheader("Analysis")
+    taba, tabb, tabc = st.tabs(["Overview", "Content", "Followers"])
+    with taba:
+        st.write("**Overview**")
+
+        data = pd.read_excel('gaming/Last 7 days.xlsx')
+
+        x_var = st.sidebar.selectbox("Select X variable for Last 7 days", data.columns)
+        y_var = st.sidebar.selectbox("Select Y variable for Last 7 days", data.columns)
+        show_regression_line = False
+    
+        z_var_options = ["None"] + list(data.columns)
+        z_var = st.sidebar.selectbox("Select Z variable for 3D charts (if applicable)", z_var_options)
+
+        tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8 = st.tabs(["Line", "Bar", "Scatterplot", "Heatmap", 
+                                                            "3D Scatterplot", "3D Lineplot", "3D Surfaceplot", "Radar chart"])
+        with tab1:
+            st.write("Lineplot for 'Last 7 days'")
+            plot_chart(data, "line", x_var, y_var)
+
+        with tab2:
+            st.write("Barplot for 'Last 7 days'")
+            plot_chart(data, "bar", x_var, y_var)
+
+        with tab3:
+            st.write("Scatterplot for 'Last 7 days'")
+            show_regression_line = st.checkbox("Show regression line for Last 7 days scatterplot (does not apply when X = Date)")
+            plot_chart(data, "scatter", x_var, y_var, show_regression_line=show_regression_line)
+
+        with tab4:
+            st.write("Heatmap for 'Last 7 days'")
+            plot_chart(data, "heatmap", x_var, y_var) 
+
+        with tab5:
+            st.write("3D Scatterplot for 'Last 7 days'")
+            if z_var != "None":
+                plot_chart(data, "scatter_3d", x_var, y_var, z_var)    
+
+        with tab6:
+            st.write("3D Lineplot for 'Last 7 days'")
+            if z_var != "None":
+                plot_chart(data, "line_3d", x_var, y_var, z_var)
+
+        with tab7:
+            st.write("3D Surfaceplot for 'Last 7 days'")
+            if z_var != "None":
+                plot_chart(data, "surface_3d", x_var, y_var, z_var)
+
+        with tab8:
+            st.write("Radar chart for 'Last 60 days'")
+            radar_columns = ['Video views', 'Profile views', 'Likes', 'Comments', 'Shares']
+            plot_radar_chart(data, radar_columns)                       
+            # Add more conditions for other specific file names if needed
+
+    with tabb:
+        st.write("**Content**")
+
+    with tabc:
+        st.write("**Followers**")