add dataset and script

analyzer.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+import pandas as pd
+import numpy as np
+import datetime
+import sys
+
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import roc_auc_score
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import precision_score
+from sklearn.metrics import recall_score
+from sklearn.metrics import f1_score
+from sklearn.metrics import confusion_matrix
+
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.linear_model import * 
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.preprocessing import StandardScaler
+from sklearn.svm import SVC
+from sklearn.neural_network import MLPClassifier
+
+
+#       load train data 
+data=pd.read_csv('traindata_sea.csv')
+
+#       add feature colomn
+data['flash'] = np.heaviside(data['lightning_count']-1,0)
+
+#       select target colomn
+wwlln=data['flash']      
+
+#       del all but sattelite data
+del data['flash']
+del data['lat']
+del data['lon']
+del data['ptime']
+del data['lightning_count']
+del data['avg_energy']
+print(data.head())
+
+folds=5         # how many folds
+scaler = StandardScaler()
+
+#       select classificator
+clf = LogisticRegression(penalty='l2', class_weight={1: 0.774})
+#clf = RandomForestClassifier(n_estimators=50)
+#clf = MLPClassifier(hidden_layer_sizes=(5,), shuffle=True,verbose=False)
+
+accur, recall, f1 = 0, 0 ,0
+matrix = np.zeros((4))
+start_time = datetime.datetime.now()
+coefs = np.empty([1,data.shape[1]])
+
+for fold in range(folds):
+    print('N_fold is:', fold)
+    X_train, X_test, y_train, y_test = train_test_split(data, wwlln, test_size=1/folds, shuffle=True)
+    X_train_scaled = scaler.fit_transform(X_train)
+    X_test_scaled = scaler.transform(X_test)
+
+    clf.fit(X_train_scaled, y_train)
+
+    try:
+        coefs += clf.coef_
+    except: 
+        print('There are NO coeffs for this clf!')
+
+    predict = clf.predict(X_test_scaled)
+    accur += precision_score(y_test, predict)
+    recall += recall_score(y_test, predict)
+    f1 += f1_score(y_test, predict)    
+    matrix += confusion_matrix(y_test, predict).ravel()
+    print (f1)
+    time = datetime.datetime.now() - start_time
+
+print (pd.DataFrame((coefs/folds)/np.max(np.abs(coefs/folds))))
+print ('accur', accur/folds)
+print ('recall', recall/folds)
+print ('f1', f1/folds)
+
+print ('TN', 'FP', 'FN', 'TP')
+print (matrix)
+print('Total events:', matrix.sum())
+print('By set:', 105295)
+if matrix.sum() == 105295:
+    print('Match! OK!')
+
+print ('time', time)