created early lambda function for running XGBboost

lambda/package.json

@@ -0,0 +1,7 @@
+{
+  "name": "ASHA-xgboost-evaluation",
+  "version": "1.0.0",
+  "description": "Trains and evaluates an XGBoost model for a parallel ASHA implementation",
+  "author": "",
+  "license": "MIT"
+}

lambda/serverless.yml

@@ -0,0 +1,15 @@
+service: ASHA-xgboost-evaluation
+
+frameworkVersion: ">=1.2.0 <2.0.0"
+
+provider:
+  name: aws
+  runtime: python3.7 # or python3.7, supported as of November 2018
+
+functions:
+  run:
+    handler: run_xgboost.run
+    events:
+      - http:
+          path: run
+          method: post

xgboost_test.py

@@ -10,12 +10,12 @@
 from sklearn.model_selection import train_test_split
 
 # read csv into dataframe
-df = pd.read_csv("./weatherAUS.csv")
+df = pd.read_csv("./weatherAUS.csv", parse_dates=['Date'])
 
 print('Size of weather data frame is :', df.shape)
 
 # drop columns with useless data (too many null values)
-df = df.drop(columns=['Sunshine','Evaporation','Cloud3pm','Cloud9am','Location','RISK_MM','Date'],axis=1)
+df = df.drop(columns=['Sunshine', 'Evaporation', 'Cloud3pm', 'Cloud9am', 'Location', 'RISK_MM', 'Date'], axis=1)
 
 # get rid of nulls
 df = df.dropna(how='any')
@@ -37,22 +37,25 @@
 scaler.fit(df)
 df = pd.DataFrame(scaler.transform(df), index=df.index, columns=df.columns)
 
+
+df.to_csv("preprocessed.csv")
 # separate data from target
 X = df.loc[:,df.columns!='RainTomorrow']
 y = df[['RainTomorrow']]
 
+# k = 5 has 84.25%, k=5 has 84.01%, 85.19% on all data ( bad cols removed), with date: 85.17
 # select the k most useful columns
-selector = SelectKBest(chi2, k=3)
-selector.fit(X, y)
-X_new = selector.transform(X)
+#selector = SelectKBest(chi2, k=10)
+#selector.fit(X, y)
+#X_new = selector.transform(X)
 
 # fit and evaluate using k_fold
 
 model = XGBClassifier()
 kfold = KFold(n_splits=5, random_state=7)
 print("Cross eval starting")
 
-results = cross_val_score(model, X_new, y, cv=kfold, verbose=3)
+results = cross_val_score(model, X, y, cv=kfold, verbose=3)
 print("Accuracy: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))