sgsg704

import matplotlib.pyplot as plt
import seaborn as sns
import datetime
from sklearn.preprocessing import LabelEncoder
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import seaborn as sns
from tensorflow.keras.layers import Dense, BatchNormalization, Dropout, LSTM
from tensorflow.keras.models import Sequential

sgsg704

data = pd.read_csv("https://cainvas-static.s3.amazonaws.com/media/user_data/hrithikgupta/weatherAUS.csv")
data.head()

sgsg704

#first of all let us evaluate the target and find out if our data is imbalanced or not
cols= ["#C2C4E2","#EED4E5"]
sns.countplot(x= data["RainTomorrow"], palette= cols)

sgsg704

# Correlation amongst numeric attributes
plt.figure(figsize=(10,10))
corrmat = data.corr()
cmap = sns.diverging_palette(260,-10,s=50, l=75, n=6, as_cmap=True)
plt.subplots(figsize=(18,18))
sns.heatmap(corrmat,cmap= cmap,annot=True, square=True,fmt="%")

sgsg704

#Parsing datetime
#exploring the length of date objects
lengths = data["Date"].str.len()
lengths.value_counts()
data['Date']= pd.to_datetime(data["Date"])
#Creating a collumn of year
data['year'] = data.Date.dt.year
# function to encode datetime into cyclic parameters. 
#As I am planning to use this data in a neural network I prefer the months and days in a cyclic continuous feature.
def encode(data, col, max_val):

sgsg704

cyclic_month = 
sns.scatterplot(x="month_sin",y="month_cos",data=data, color="#C2C4E2")
cyclic_month.set_title("Cyclic Encoding of Month")
cyclic_month.set_ylabel("Cosine Encoded Months")
cyclic_month.set_xlabel("Sine Encoded Months")

sgsg704

cyclic_day = sns.scatterplot(x='day_sin',y='day_cos',data=data, color="#C2C4E2")
cyclic_day.set_title("Cyclic Encoding of Day")
cyclic_day.set_ylabel("Cosine Encoded Day")
cyclic_day.set_xlabel("Sine Encoded Day")

sgsg704

# Get list of categorical variables
s = (data.dtypes == "object")
object_cols = list(s[s].index)
print("Categorical variables:")
print(object_cols)

sgsg704

# Get list of categorical variables
s = (data.dtypes == "object")
object_cols = list(s[s].index)
print("Categorical variables:")
print(object_cols)

sgsg704

# Apply label encoder to each column with categorical data
label_encoder = LabelEncoder()
for i in object_cols:
    data[i] = label_encoder.fit_transform(data[i])
    
data.info()