import pandas as pd

dataframe = pd.read_csv("https://raw.githubusercontent.com/ujwalnk/MachineLearning101/main/data/01%20Weather%20Data.csv")
dataframe.head()

dataframe = dataframe.dropna()
dataframe.isnull().sum(), dataframe.count()

dataframe = dataframe.drop("Date", axis=1)

dataframe = dataframe.drop_duplicates()
dataframe.sort_values("RainTomorrow", axis=0, ascending=True, inplace=True)
dataframe["RainTomorrow"].value_counts()

from sklearn.model_selection import train_test_split

# Import label encoder
from sklearn import preprocessing

label_encoder = preprocessing.LabelEncoder()
dataframe["RainTomorrow"] = label_encoder.fit_transform(dataframe["RainTomorrow"])

y = dataframe["RainTomorrow"]
X = dataframe = pd.get_dummies(dataframe.drop("RainTomorrow", axis=1))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)

X_train.shape, X_test.shape, y_train.shape, y_test.shape

from sklearn.linear_model import SGDClassifier as clf

sgd_model = clf()
sgd_model.fit(X_train, y_train)

sgd_model.score(X_test, y_test)

sgd_model.coef_