Create app.py

app.py

@@ -0,0 +1,53 @@
+import pandas as pd
+import numpy as np
+import csv
+import json
+import matplotlib.pyplot as plt
+import ast
+from sklearn import linear_model
+
+
+df = pd.read_csv('emily_election.csv')
+
+
+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())
+
+#feature 3 (for later)
+df['audience_size'] = df['cumulative_est_audience'].apply(lambda d: ast.literal_eval(d))
+df['audience_size'] = df['audience_size'].apply(lambda d: np.array(list(d.values())).sum())
+
+#data = df[['runtime', 'spend', 'impressions']]
+data = df[['runtime', 'spend', 'audience_size','impressions']]
+
+msk = np.random.rand(len(data)) < 0.8
+train = data[msk]
+test = data[~msk]
+
+
+#new_train = train[train['impressions'] < 1000000]
+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
+
+regr = linear_model.LinearRegression()
+new_train['log_runtime'] = np.log(new_train['runtime'])
+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)
+x = np.asanyarray(new_train[['log_runtime', 'log_spend']])
+y = np.asanyarray(new_train[['log_impressions']])
+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)))
+
+
+