kurasaiteja

best_churn["scaled_tran"] = (best_churn["no_of_transactions"] - best_churn["no_of_transactions"].min())/ (best_churn["no_of_transactions"].max() - best_churn["no_of_transactions"].min())

best_churn["scaled_amount"] = (best_churn["amount_spent"] -best_churn["amount_spent"].min()) / (best_churn["amount_spent"].max() - best_churn["amount_spent"].min())

best_churn["score"] = 100*(.5*best_churn["scaled_tran"] + .5*best_churn["scaled_amount"])

best_churn.sort_values("score", inplace=True, ascending=False)

kurasaiteja

best_churn = pd.DataFrame(last_transaction)
#Convert the cutoff_day to date time format
cutoff_day = pd.to_datetime("01/05/20")
def d(date):
    if date < cutoff_day:
        return 1
    else:
        return 0
# Creating a boolean column to denote churn status
best_churn["churned"] = best_churn["transaction_date"].apply(d)

kurasaiteja

import numpy as np
def standard_deviation(array):
    mean = sum(array) / len(array)
    distances = []
    for value in array:
        # appending square of distances
        distances.append(((value - mean)**2))
    return sum(distances) / len(distances)
  

kurasaiteja

def variance(array):
    mean = sum(array) / len(array)
    distances = []
    for value in array:
        # appending square of distances
        distances.append(((value - mean)**2))
    return sum(distances) / len(distances)
  

input = [1,1,1,1,1,1,1,1,1,21]

kurasaiteja

def visualize_emoji(data):
	total_emojis_list = list([a for b in messages_df.emoji for a in b])
	emoji_dict = dict(Counter(total_emojis_list))
	emoji_dict = sorted(emoji_dict.items(), key=lambda x: x[1], reverse=True)
	emoji_df = pd.DataFrame(emoji_dict, columns=['emoji', 'count'])
	fig = px.pie(emoji_df, values='count', names='emoji')
	fig.update_traces(textposition='inside', textinfo='percent+label')
	fig.update_layout(
    	margin=dict(
        	l=5,

kurasaiteja

st.title('Whatsapp Group Chat Analysis')
st.markdown('Analysis on Exported chats to understand texting patterns of users.')
st.set_option('deprecation.showfileUploaderEncoding', False)

st.sidebar.title("Analyze:")
st.sidebar.markdown("This app is use to analyze your WhatsApp Group Chats")

st.sidebar.markdown('[![Saiteja Kura]\
                    (https://img.shields.io/badge/Author-@SaitejaKura-gray.svg?colorA=gray&colorB=dodgerblue&logo=github)]\
                    (https://github.com/kurasaiteja/Whatsapp-Analysis/)')

kurasaiteja

fig = go.Figure()
fig.add_trace(go.Bar(
    x=columns,
    y=averages_AP,
    name="AP",
    marker_color='indianred'
))
fig.add_trace(go.Bar(
    x=columns,
    y=averages_Telangana,

kurasaiteja

fig = go.Figure()
fig.add_trace(go.Scatter(
    x=[lockdown1,lockdown2,lockdown3,lockdown4,unlock1,unlock2],
    y=[39,39,39,39,39,39],
    text=["Lockdown 1","Lockdown 2","Lockdown 3", "Lockdown 4", "Unlock 1", "Unlock 2"],
    mode="text",
))

l = df_india_Telangana.columns

kurasaiteja

columns = ["Recreation","Grocery_and_Pharmacy","Parks","Transit_stations","Workplaces","Residential"]
for i in columns:
  fig = px.box(df_india_Telangana_and_AP, x="Lockdown", y=i, color="State",width=600,height=400,title=i,template="plotly_dark")# or "inclusive", or "linear" by default

  fig.show()

kurasaiteja

def datephase(date):
  if date < "2020-03-22":
    return "Pre Lockdown" 
  elif date < "2020-04-15":
    return "Lockdown Phase 1"
  elif date < "2020-05-04":
    return "Lockdown Phase 2"
  elif date < "2020-05-18":
    return "Lockdown Phase 3"
  elif date < "2020-06-01":