sgsg704

features = data.drop(['RainTomorrow', 'Date','day', 'month'], axis=1) # dropping target and extra columns
target = data['RainTomorrow']
#Set up a standard scaler for the features
col_names = list(features.columns)
s_scaler = preprocessing.StandardScaler()
features = s_scaler.fit_transform(features)
features = pd.DataFrame(features, columns=col_names)
features.describe().T

#Detecting outliers

sgsg704

#full data for 
features["RainTomorrow"] = target
#Dropping with outlier
features = features[(features["MinTemp"]<2.3)&(features["MinTemp"]>-2.3)]
features = features[(features["MaxTemp"]<2.3)&(features["MaxTemp"]>-2)]
features = features[(features["Rainfall"]<4.5)]
features = features[(features["Evaporation"]<2.8)]
features = features[(features["Sunshine"]<2.1)]
features = features[(features["WindGustSpeed"]<4)&(features["WindGustSpeed"]>-4)]
features = features[(features["WindSpeed9am"]<4)]

sgsg704

X = features.drop(["RainTomorrow"], axis=1)
y = features["RainTomorrow"]
# Splitting test and training sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)
X.shape

sgsg704

early_stopping = callbacks.EarlyStopping(
    min_delta=0.001, # minimium amount of change to count as an improvement
    patience=20, # how many epochs to wait before stopping
    restore_best_weights=True,
)
# Initialising the NN
model = Sequential()
# layers
model.add(Dense(units = 32, kernel_initializer = 'uniform', activation = 'relu', input_dim = 26))
model.add(Dense(units = 32, kernel_initializer = 'uniform', activation = 'relu'))

sgsg704

history_df = pd.DataFrame(history.history)
plt.plot(history_df.loc[:, ['loss']], "#BDE2E2", label='Training loss')
plt.plot(history_df.loc[:, ['val_loss']],"#C2C4E2", label='Validation loss')
plt.title('Training and Validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend(loc="best")
plt.show()

sgsg704

history_df = pd.DataFrame(history.history)
plt.plot(history_df.loc[:, ['accuracy']], "#BDE2E2", label='Training accuracy')
plt.plot(history_df.loc[:, ['val_accuracy']], "#C2C4E2", label='Validation accuracy')
plt.title('Training and Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

sgsg704

# Predicting the test set results
y_pred = model.predict(X_test)
y_pred = (y_pred > 0.5)
# confusion matrix
cmap1 = sns.diverging_palette(260,-10,s=50, l=75, n=5, as_cmap=True)
plt.subplots(figsize=(12,8))
cf_matrix = confusion_matrix(y_test, y_pred)
sns.heatmap(cf_matrix/np.sum(cf_matrix), cmap = cmap1, annot = True, annot_kws = {'size':15})

sgsg704

model.save('rain.h5')
!deepCC rain.h5

sgsg704

model.summary()

sgsg704

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
import seaborn as sns
import os
plt.rcParams['figure.figsize']=(12,5)
import warnings
warnings.filterwarnings("ignore")