Update app.py

app.py

@@ -1,4 +1,4 @@
-#import streamlit as st
+import streamlit as st
 import pandas as pd
 import numpy as np
 import csv
@@ -15,7 +15,7 @@ df = pd.read_csv('emily_election.csv')
 
 #loaded_model = pickle.load(open(filename, 'rb'))
 
-
+df['spend'] = df['cum_spend']
 df['runtime'] = df['cumulative_ad_runtime'].apply(lambda s: int(s.split('days')[0]))
 df['impressions'] = df['cumulative_impressions_by_region'].apply(lambda d: ast.literal_eval(d))
 df['impressions'] = df['impressions'].apply(lambda d: np.array(list(d.values())).sum())
@@ -33,12 +33,11 @@ test = data[~msk]
 
 
 #new_train = train[train['impressions'] < 1000000]
-train['spend'] = pd.to_numeric(train['spend'],errors='coerce')
+train['spend'] = train['spend'].astype('float')
 
 
 new_train = train[(train['spend'] > 250)]
 new_train = new_train[new_train['runtime']>4]
-new_train.shape
 
 
 #this model predicts impressions given the runtime and the spend
@@ -49,17 +48,14 @@ new_train['log_spend'] = np.log(new_train['spend'])
 new_train['log_impressions'] = np.log(new_train['impressions'])
 new_train.replace([np.inf, -np.inf], np.nan, inplace=True)
 new_train.dropna(inplace=True)
+print(new_train.to_string())
 x = np.asanyarray(new_train[['log_runtime', 'log_spend']])
 y = np.asanyarray(new_train[['log_impressions']])
-print(x)
-regr.fit(x, y)
-#y_pred= regr.predict(new_train[['log_runtime', 'log_spend']])
-
-
-# # The coefficients
-#print(regr.coef_)
-#print('R-squared score: %.2f' % regr.score(x, y))
-#print('Standard Deviation: %.2f' % np.sqrt(sum((y - y_pred)**2) / (len(y) - 2)))
-
 
+regr.fit(x, y)
+spend = st.number_input('Enter Spend (in dollars): ')
+runtime = st.number_input('Enter runtime (in days)')
 
+if spend and runtime:
+  pred= regr.predict([np.log([spend, runtime])])
+  st.write('70% confidence interval for number of impressions is: {} to {} hits'.format(int(np.exp(pred[0][0]-1.65)), int(np.exp(pred[0][0]+1.65))))