Rain.py

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

# This code can be run at https://www.kaggle.com/cristiancalin/using-logistic-regression-to-predict-rainfall

import numpy as np  #linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import torch
from tqdm import tqdm
from pylab import rcParams
import matplotlib.pyplot as plt
from matplotlib import rc
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, classification_report
from torch import nn, optim
import torch.nn.functional as F

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

df = pd.read_csv('../input/weather-dataset-rattle-package/weatherAUS.csv')

# We must decide what data we need in order to deduce whether it will rain tomorrow or not.
# We shall only consider rainfall, humidity, pressure, rain today and rain tomorrow.
# We aren't considering whether there were clouds or not because the data is incomplete, and what we have can already be turned into a model.
# After deleting all the unnecessary data, we shall also turn the data into numerical values.

cols = ['Rainfall', 'Humidity3pm', 'Pressure9am', 'RainToday', 'RainTomorrow']
df = df[cols]
df['RainToday']=df['RainToday'].replace({'Yes':1, 'No':0})
df['RainTomorrow']=df['RainTomorrow'].replace({'Yes':1, 'No':0})
df=df.dropna()

# We shall use the first four indices in order to determine the fifth one, whether it will rain tomorrow.
# We shall split the data into a training set and a test set using scikit-learn.

X=df[['Rainfall','Humidity3pm','Pressure9am', 'RainToday']]
y=df[['RainTomorrow']]
X_train, X_test, y_train, y_test=train_test_split(X, y, test_size=0.2, random_state=21)

# Since we have two possible outcomes (whether it will rain or not), we shall use the Logistic Regression to predict the weather.

logreg=LogisticRegression()
logreg.fit(X_train, y_train)
y_pred=logreg.predict(X_test)
print(classification_report(y_test, y_pred))
print(confusion_matrix(y_test, y_pred))

# We observe that, through our model, we obtain a very large amount of false positives (even bigger than the number of true negatives!). 
# This is mainly due to the fact that there are very few days in which it rains.