Spaces:
Sleeping
Sleeping
File size: 15,477 Bytes
e324f43 cdd172b e324f43 cdd172b e324f43 1c6bb71 83c234f 1c6bb71 e324f43 c095d8d e324f43 c095d8d cdd172b c095d8d cdd172b c095d8d b68bb4d c095d8d cdd172b b68bb4d cdd172b c095d8d fc7ea67 cdd172b b68bb4d add8b88 c095d8d add8b88 1c6bb71 c095d8d add8b88 c095d8d fc7ea67 add8b88 c095d8d add8b88 c095d8d add8b88 cdd172b add8b88 fc7ea67 c095d8d add8b88 c095d8d e324f43 c095d8d add8b88 c095d8d e324f43 c095d8d add8b88 c095d8d 1c6bb71 c095d8d e324f43 add8b88 cdd172b add8b88 b68bb4d 1c6bb71 b68bb4d add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 cdd172b add8b88 e324f43 add8b88 cdd172b add8b88 1c6bb71 e324f43 add8b88 fc7ea67 cdd172b add8b88 cdd172b add8b88 fc7ea67 add8b88 cdd172b add8b88 fc7ea67 add8b88 cdd172b add8b88 cdd172b add8b88 fc7ea67 add8b88 59c76fe cdd172b add8b88 cdd172b add8b88 fc7ea67 cdd172b add8b88 fc7ea67 cdd172b add8b88 cdd172b add8b88 e324f43 1c6bb71 e324f43 60ef30a e324f43 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 |
import streamlit as st
import pandas as pd
import joblib
from preprocessText import preprocess
from apiSearch import get_metadata,get_trending_videos
import base64
import requests
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
# Load the model
def read_model(region):
if(region == "United States"):
model = joblib.load('85pct.pkl')
return model
# Define the categories
categories = {
'Film & Animation': 1,
'Autos & Vehicles': 2,
'Music': 10,
'Pets & Animals': 15,
'Sports' : 17,
'Travel & Events' : 19,
'Gaming' : 20,
'People & Blogs' : 22,
'Comedy' : 23,
'Entertainment' : 24,
'News & Politics' : 25,
'Howto & Style' : 26,
'Education' : 27,
'Science & Technology' : 28,
'Nonprofits & Activism' : 29
}
# Create the Streamlit web application
def main():
st.set_page_config(layout="wide")
st.markdown(
f"""
<style>
@import url('https://fonts.googleapis.com/css2?family=Roboto:wght@400;700&display=swap');
@import url('https://fonts.googleapis.com/css2?family=YouTube+Sans&display=swap');
html, body, [class*="css"] {{
font-family: 'Roboto', sans-serif;
}}
[data-testid="stAppViewContainer"] > .main {{
background-color : white;
}}
p{{
font-family: 'Roboto', sans-serif;
text-weight: bold;
font-size: 25px;
}}
body{{
display: flex;
justify-content: center;
align-items: center;
text-align: center;
}}
h1{{
text-align: center;
color: #d72324;
}}
img{{
max-width: 100%;
max-height: 100%;
}}
.stButton > button {{
background-color: #d72324;
color:white;
font-weight: bold;
width: 500px;
height: 50px;
}}
.stDownloadButton > button{{
background-color: #e7e7e7;
color:black;
font-weight: bold;
width: 150px;
height: 35px;
float: right;
}}
.stButton > button:hover {{
background-color: white;
color:#d72324;
}}
.my-container {{
border: 2px solid #d72324;
padding: 10px;
}}
</style>
""",
unsafe_allow_html=True
)
st.markdown("<body><img style = 'max-width: 20%;max-height: 20%;text-align: center;' src=\"https://media.tenor.com/U7OFq772kIEAAAAj/sweet-dreams.gif\"></body>",unsafe_allow_html=True)
st.markdown("<h1>YouTube Trend Prediction</h1>", unsafe_allow_html=True)
@st.cache_data
def convert_df(df):
return df.to_csv(index=False).encode('utf-8')
# Sidebar menu options
menu_options = ["Predict", "Trending", "Visualize"]
selected_option = st.sidebar.selectbox("Menu", menu_options)
# Input fields
if selected_option == "Predict":
region = st.sidebar.selectbox("Select Region", ['United States'])
model = read_model(region)
with st.container():
col1, col2, col3 = st.columns(3)
getTitle, getDuration, getCategory = "", 0.00, 1
getThumbnailUrl = ""
with col1:
url = st.text_input("URL", placeholder="Enter a video URL")
if url:
metadata = get_metadata(url)
if not metadata.empty:
getTitle = metadata['title'].iloc[0]
getDuration = metadata['duration'].iloc[0]
category_id = metadata['category_id'].iloc[0]
getThumbnailUrl = metadata['thumbnail_link'].iloc[0]
getCategory = int(category_id)
getDescription = metadata['description'].iloc[0]
if getThumbnailUrl is not None:
picture = get_picture_from_url(getThumbnailUrl)
if picture:
st.image(picture, caption='Thumbnail captured', width=320, channels="BGR")
with col2:
title = st.text_input("Title", placeholder="Enter a video title", value=getTitle)
duration = st.number_input("Duration (in seconds)", min_value=0.0, value=getDuration)
category = st.selectbox(
"Category", list(categories.keys()), index=list(categories.values()).index(getCategory)
)
with col3:
picture = st.file_uploader("Upload Picture", type=["jpg", "jpeg", "png"])
if picture is not None:
st.picture(picture, caption='Thumbnail Uploaded', width=400, channels="BGR")
# Convert category to category ID
categoryId = categories[category]
if st.button("Predict"):
# Perform prediction
if title is None or title.strip() == "" and duration == 0:
st.warning("Please enter a title and duration.")
else:
if title is None or title.strip() == "":
st.warning("Please enter a title")
if duration == 0:
st.warning("Please enter a duration.")
else:
prediction = predict_trend(model,title, duration, categoryId)
if prediction[0] == 1:
st.success("This video is predicted to be a trend!")
st.markdown("")
else:
st.info("This video is predicted not to be a trend.")
st.markdown("")
elif selected_option == "Trending":
tab1, tab2 = st.tabs(["Trending Board", "Video Info"])
country_code = st.sidebar.selectbox("Select Country Code", ['US', 'CA', 'GB', 'DE', 'FR', 'RU', 'BR', 'IN', 'MY', 'SG', 'JP', 'KR'])
with st.container():
with tab1:
st.write("Top 10 Trending Videos")
df = get_trending_videos(country_code)
st.dataframe(df)
csv = convert_df(df)
st.download_button(
"Download",
csv,
"top10Trending.csv",
"text/csv",
key='download-csv'
)
with tab2:
if df is not None:
selected_video_title = st.selectbox("Select a Video", df['title'])
selected_video = df[df['title'] == selected_video_title].iloc[0]
else:
st.error('Failed to retrieve trending videos.')
col4, col5 = st.columns(2)
with col4:
if selected_video is not None:
image = get_picture_from_url(selected_video['thumbnail_link'])
if image:
st.image(image, caption='Thumbnail captured', width=400, channels="BGR")
with col5:
st.write("Title:", selected_video['title'])
category_name = next(
(key for key, value in categories.items() if value == selected_video['category_id']), 'Unknown Category'
)
st.write("Category:", category_name)
st.write("Duration:", selected_video['duration'])
elif selected_option == "Visualize":
with st.container():
tab3, tab4, tab5, tab6 = st.tabs(["Best Category", "Best Duration","Best Title","Best Title Length"])
with tab3:
col6, col7 = st.columns(2)
with col6:
show_top_category()
with col7:
show_best_category()
with tab4:
col8, col9 = st.columns(2)
with col8:
show_top_duration()
with col9:
show_best_duration()
with tab5:
col10, col11 = st.columns(2)
with col10:
show_top_title()
with col11:
show_best_title()
with tab6:
col12, col13 = st.columns(2)
with col12:
show_top_titleLength()
with col13:
show_best_titleLength()
def get_picture_from_url(url):
try:
response = requests.get(url)
image_data = response.content
return image_data
except:
return None
def get_top_category():
topCategory = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topCategory.csv')
topCategory_sorted = topCategory.sort_values('predicted_prob')
topCategory_sorted['rank'] = range(1, len(topCategory_sorted) + 1)
topCategory_sorted['category_name'] = topCategory_sorted['category_id'].map(lambda x: next((key for key, value in categories.items() if value == x), 'Unknown Category'))
return topCategory_sorted
def show_top_category():
topCategory_sorted = get_top_category()
color_palette = sns.color_palette('Set2', len(topCategory_sorted['category_id'].unique()))
fig, ax = plt.subplots(figsize=(8, 5))
sns.barplot(data=topCategory_sorted, x='rank', y='predicted_prob', hue='category_name', palette=color_palette)
plt.xlabel('Rank')
plt.ylabel('Predicted Probability')
plt.title('Top Categories')
st.pyplot(fig)
def show_best_category():
topCategory_sorted = get_top_category()
top_3_categories = topCategory_sorted.sort_values('predicted_prob', ascending=False).head(3)
top_3_categories = top_3_categories['category_name'].head(3)
st.header("Top 3 Categories")
for category_id in top_3_categories:
color = '#339933' if category_id == top_3_categories.iloc[0] else '#ffcc33' if category_id == top_3_categories.iloc[1] else '#ff9900'
st.write(f"<span style='color:{color};font-weight:bold;'>{category_id}</span>", unsafe_allow_html=True)
def get_top_duration():
topDurationsorted = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topDuration.csv')
topDurationsorted = topDurationsorted.sort_values('predicted_prob', ascending=False)
return topDurationsorted
def show_top_duration():
topDuration_sorted = get_top_duration()
sns.set(style='whitegrid')
plt.figure(figsize=(10, 6))
sns.barplot(x='duration_range', y='predicted_prob',data=topDuration_sorted)
plt.xlabel('Duration')
plt.ylabel('Predicted Probability')
plt.title('Top Durations')
plt.xticks(rotation=45)
plt.show()
st.pyplot(plt)
def show_best_duration():
topDurationRange = get_top_duration()
top_3_durationRange = topDurationRange.sort_values('predicted_prob', ascending=False).head(3)
top_3_range = top_3_durationRange['duration_range'].head(3)
st.header("Top 3 Duration Range")
for range in top_3_range:
color = '#339933' if range == top_3_range.iloc[0] else '#ffcc33' if range == top_3_range.iloc[1] else '#ff9900'
st.write(f"<span style='color:{color};font-weight:bold;'>{range}</span>", unsafe_allow_html=True)
def get_top_title():
topTitle = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topTitle.csv')
topTitle_sorted = topTitle.sort_values('Importance Score', ascending=False)
return topTitle_sorted
def show_top_title():
topTitle_sorted = get_top_title()
sns.set(style="whitegrid")
plt.figure(figsize=(8, 6))
sns.barplot(x='Importance Score', y='Feature', data=topTitle_sorted, palette="rocket")
plt.xlabel('Importance Score', fontsize=12)
plt.ylabel('Feature', fontsize=12)
plt.title('Top Title Features', fontsize=14)
plt.tight_layout()
st.pyplot(plt)
def show_best_title():
topTitle_sorted = get_top_title()
top_3_keyword = topTitle_sorted.sort_values('Importance Score', ascending=False).head(3)
top_3_keyword = topTitle_sorted['Feature'].head(3)
st.header("Top 3 Keyword")
for feature in top_3_keyword:
color = '#339933' if feature == top_3_keyword.iloc[0] else '#ffcc33' if feature == top_3_keyword.iloc[1] else '#ff9900'
st.write(f"<span style='color:{color};font-weight:bold;'>{feature}</span>", unsafe_allow_html=True)
def round_interval(interval_str):
start, end = map(float, interval_str.strip('()[]').split(','))
return f"({int(start)}, {int(end)})"
def get_top_titleLength():
topTitleLength = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topTitleLength.csv')
title_length_ranges = topTitleLength['titleLength']
predicted_probs = topTitleLength['predicted_prob']
rounded_ranges = [round_interval(range_val) for range_val in title_length_ranges]
data = {
'rounded_ranges': rounded_ranges,
'predicted_probs': predicted_probs
}
topTitleLength = pd.DataFrame(data)
sorted_titleLength = topTitleLength.sort_values(by='predicted_probs', ascending=False)
return sorted_titleLength
def show_top_titleLength():
topTitleLength = get_top_titleLength()
sns.set(style='whitegrid')
plt.figure(figsize=(10, 6))
sns.barplot(x='rounded_ranges', y='predicted_probs',data=topTitleLength)
plt.xlabel('Title Length Range')
plt.ylabel('Predicted Probability')
plt.title('Top 5 Ranges for Title Length vs. Predicted Probability')
plt.xticks(rotation=45)
plt.show()
st.pyplot(plt)
def show_best_titleLength():
topTitleLength = get_top_titleLength()
top_3_titleLength = topTitleLength.sort_values('predicted_probs', ascending=False).head(3)
top_3_range = top_3_titleLength['rounded_ranges'].head(3)
st.header("Top 3 Title Length Range")
for range in top_3_range:
color = '#339933' if range == top_3_range.iloc[0] else '#ffcc33' if range == top_3_range.iloc[1] else '#ff9900'
st.write(f"<span style='color:{color};font-weight:bold;'>{range}</span>", unsafe_allow_html=True)
# Function to make predictions
def predict_trend(model,title, duration, category_id):
duration = str(duration)
category_id = int(category_id)
clean_new_title = preprocess(title)
clean_new_title_str = ' '.join(clean_new_title)
data = {
'cleanTitle': [clean_new_title_str],
'titleLength' : [len(title)],
'categoryId': [category_id],
'duration': [duration]
}
data = pd.DataFrame(data)
data['categoryId'] = data['categoryId'].astype('category')
data['duration'] = data['duration'].astype('float64')
# Make the prediction
print(model.predict_proba(data))
prediction = model.predict(data)
return prediction
if __name__ == "__main__":
main()
|