Assignment_1_Machine_Learning

import pandas as pd
pd.set_option('display.max_columns', 15)
data = pd.read_csv("train.csv")
data_test=pd.read_csv("test.csv")
print(data.dtypes) # Finding datatypes for all feautures


print(data["PassengerId"].isnull().values.any()) # Null Value is there or not
print(data["Survived"].isnull().values.any())
print(data["Pclass"].isnull().values.any())
print(data["Name"].isnull().values.any())
print(data["Sex"].isnull().values.any())
print(data["Age"].isnull().values.any())
print(data["SibSp"].isnull().values.any())
print(data["Parch"].isnull().values.any())
print(data["Ticket"].isnull().values.any())
print(data["Fare"].isnull().values.any())
print(data["Cabin"].isnull().values.any())
print(data["Embarked"].isnull().values.any())

print("\n")
print("\n")
print("\n")
print("\n")


print(data_test["PassengerId"].isnull().values.any()) # Null Value is there or not
#print(data_test["Pclass"].isnull().values.any())
print(data_test["Name"].isnull().values.any())
print(data_test["Sex"].isnull().values.any())
print(data_test["Age"].isnull().values.any())
print(data_test["SibSp"].isnull().values.any())
print(data_test["Parch"].isnull().values.any())
print(data_test["Ticket"].isnull().values.any())
print(data_test["Fare"].isnull().values.any())
print(data_test["Cabin"].isnull().values.any())
print(data_test["Embarked"].isnull().values.any())

print("\n")

print("\n")

print(data.describe())


print(data["Age"].count())
print(data["Age"].mean())
print(data["Age"].std())
print(data["Age"].min())
print(data["Age"].max())
print(data["Age"].quantile(.25))
print(data["Age"].quantile(.50))
print(data["Age"].quantile(.75))


print(data["SibSp"].count())
print(data["SibSp"].mean())
print(data["SibSp"].std())
print(data["SibSp"].min())
print(data["SibSp"].max())
print(data["SibSp"].quantile(.25))
print(data["SibSp"].quantile(.50))
print(data["SibSp"].quantile(.75))


print(data["Parch"].count())
print(data["Parch"].mean())
print(data["Parch"].std())
print(data["Parch"].min())
print(data["Parch"].max())
print(data["Parch"].quantile(.25))
print(data["Parch"].quantile(.50))
print(data["Parch"].quantile(.75))


print(data["Fare"].count())
print(data["Fare"].mean())
print(data["Fare"].std())
print(data["Fare"].min())
print(data["Fare"].max())
print(data["Fare"].quantile(.25))
print(data["Fare"].quantile(.50))
print(data["Fare"].quantile(.75))




#print(data['Fare'].count)
#print(data.isnull().sum())

#filter = data["Name"]=="Braund, Mr. Owen Harris"
#print(data.where(filter))

#print(data[(data["Age"]==54) & (data["Sex"]=="male")].head(15))




print(data["Survived"].count())
print(data["Survived"].nunique()) # Number of unique values
print(data["Survived"].value_counts().idxmax()) #Most frequent value

#print(data["Survived"].value_counts()) #Most frequent value

print(data["Pclass"].count())
print(data["Pclass"].nunique()) # Number of unique values
print(data["Pclass"].value_counts().idxmax()) #Most frequent value


print(data["Sex"].count())
print(data["Sex"].nunique()) # Number of unique values
print(data["Sex"].value_counts().idxmax()) #Most frequent value

print(data["Embarked"].count())
print(data["Embarked"].nunique()) # Number of unique values
print(data["Embarked"].value_counts().idxmax()) #Most frequent value



data.drop(["Survived"], axis=1)
combine=pd.concat([data,data_test])

print(combine.describe())


print(combine["Survived"].count())
print(combine["Survived"].nunique()) # Number of unique values
print(combine["Survived"].value_counts().idxmax()) #Most frequent value

#print(data["Survived"].value_counts()) #Most frequent value

print("\n")

print(combine["Pclass"].count())
print(combine["Pclass"].nunique()) # Number of unique values
print(combine["Pclass"].value_counts().idxmax()) #Most frequent value

print("\n")

print(combine["Sex"].count())
print(combine["Sex"].nunique()) # Number of unique values
print(combine["Sex"].value_counts().idxmax()) #Most frequent value

print("\n")

print(combine["Embarked"].count())
print(combine["Embarked"].nunique()) # Number of unique values
print(combine["Embarked"].value_counts().idxmax()) #Most frequent value



print(combine["Survived"].describe())
print(combine["Embarked"].describe())
print(combine["Pclass"].describe())
print(combine["Sex"].describe())