aniruddha27

# Number of documents in restaurants collection
db.restaurants.find().count()  # 25359

# Number of documents in neighborhoods collection
db.neighborhoods.find().count()  # 195

aniruddha27

# List the collecitons in the database
db.list_collection_names()

aniruddha27

# Load restaurants database
db = client.sample_restaurants

aniruddha27

# List all databases
client.list_database_names()

aniruddha27

# importing the required libraries
import pymongo
import pprint
import json
import warnings
warnings.filterwarnings('ignore')
from pprint import pprint

# connect to the mongoclient
client = pymongo.MongoClient(<connection_string>)

aniruddha27

# Plotting hashtags counts

data = df_pivot.nlargest(columns="Tweet_Id", n = 15) 

# Creating bar graph
plt.figure(figsize=(16,5))
ax = sns.barplot(data=data, x= "Hashtags", y = "Tweet_Id", palette=("Reds_d"))

# Altering the visual elements
sns.set_context("poster")

aniruddha27

# Unique hashtag counts
table = df_tags.pivot_table(index="Hashtags",values='Tweet_Id',aggfunc=len)

# Convert pivot table to dataframe
df_pivot = pd.DataFrame(table.to_records())

df_pivot.head()

aniruddha27

# Querying hashtags from database
data_tags = DbConnect("SELECT Tweet_Id, Hashtag FROM TwitterEntity;")

df_tags = pd.DataFrame(columns=['Tweet_Id','Hashtags'])

for data in data_tags:
    index = len(df_tags)
    df_tags.loc[index,'Tweet_Id'] = data[0]
    df_tags.loc[index,'Hashtags'] = data[1]
    

aniruddha27

# Sentiment analysis using Textblob
def sentiment(tweet):

    analysis = TextBlob(tweet)
    if analysis.sentiment.polarity > 0:
        return 1
    elif analysis.sentiment.polarity == 0:
        return 0
    else:
        return -1

aniruddha27

# Most commomly occuring words
def keywords():
    all_words = ' '.join([text for text in df_tweet['Clean_Tweet']])
    wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(all_words)

    plt.figure(figsize=(10, 7))
    plt.imshow(wordcloud, interpolation="bilinear")
    plt.axis('off')
    plt.show()