import pandas as pd
import numpy as np
%config InlineBackend.figure_format = 'svg'

labels = ['a', 'b', 'c']
my_list = [10, 20, 30]
arr = np.array([10, 20, 30])
d = {'a': 10, 'b': 20, 'c': 30}

pd.Series(data=my_list)

pd.Series(data=my_list, index=labels)

pd.Series(arr,labels)

pd.Series(d)

pd.Series([sum,print,len])

ser1 = pd.Series([1, 2, 3, 4], index=['USA', 'Germany', 'USSR', 'Japan'])
ser1

ser2 = pd.Series([1, 2, 5, 4], index=['USA', 'Germany', 'Italy', 'Japan'])
ser2

ser1['USA']

ser1 + ser2

ser1[:2]

pd.DataFrame?

df = pd.DataFrame(np.random.randn(5,4),index='A B C D E'.split(),columns='W X Y Z'.split())

df

    !pip3 install --upgrade beautifulsoup4

import bs4

titanic_full_df = pd.read_csv("https://nagornyy.me/datasets/titanic.csv", sep=",")

titanic_full_df.shape

titanic_full_df.info()

titanic_full_df.describe()

titanic_full_df.columns

titanic_full_df.dtypes

titanic_full_df.head()

titanic_full_df.tail()

titanic_full_df.isnull().sum()

titanic_full_df.sample(5)

titanic_full_df.sample(5)

titanic_full_df["Age"].head()

type(titanic_df["Age"])

# Pass a list of column names
titanic_full_df[["Age", "Sex"]].head()

titanic_full_df["Relatives"] = titanic_full_df["SibSp"] + titanic_full_df["Parch"]

titanic_full_df[["SibSp", "Parch", "Relatives"]].head()

titanic_full_df.drop("Relatives", axis=1).head()  # inplace=True

titanic_full_df.index.tolist()[:10]

titanic_full_df.loc[442 : 450 : 2, ["Age", "Sex"]]

titanic_full_df.set_index(["Embarked"]).loc["S"].head()

titanic_full_df.iloc[0]

titanic_full_df.iloc[[564, 442]]

titanic_full_df.loc[[564, 442], ["Name", "Sex"]]

titanic_full_df == 1

titanic_full_df.Survived == 1

titanic_full_df[titanic_full_df["Survived"] == 0].head()

titanic_full_df[titanic_full_df["Survived"] == 1]["Sex"].value_counts()

titanic_full_df[(titanic_full_df["Fare"] > 100)
                | (titanic_full_df["Name"].str.find("Master") != -1)].head()

titanic_full_df["Embarked"].unique()

titanic_full_df["Embarked"].nunique()

titanic_full_df["Survived"].value_counts()

titanic_full_df["Pclass"].value_counts()

titanic_full_df["Pclass"].replace({1: "Элита", 2: "Средний класс", 3: "Работяги"}, inplace=True)

titanic_full_df["Pclass"].value_counts()

titanic_full_df["Fare"].apply(lambda x: "Дёшево" if x < 20 else "Дорого")

titanic_full_df["Fare_Bin"] = titanic_full_df["Fare"].apply(lambda x: "Дёшево" if x < 20 else "Дорого")

titanic_full_df.sort_values(by="Fare", ascending=False)

titanic_full_df.isnull().any()

titanic_full_df.dropna().head()

titanic_full_df.dropna(subset=["Age", "Sex"]).head()

titanic_full_df.dropna(thresh=12).head()  # не менее 12 заполненных колонок

titanic_full_df.fillna("ПРОПУСК").head()

titanic_full_df["Age"].mean()

titanic_full_df["Age"].fillna(value=titanic_df["Age"].mean()).head()

titanic_full_df[["Sex", "Survived"]].pivot_table(index=["Sex"], columns=["Survived"], aggfunc=len)

titanic_full_df[["Sex", "Survived", "Age"]].pivot_table(
    values=["Age"], index=["Sex"], columns=["Survived"], aggfunc="mean")

titanic_full_df.groupby("Pclass")

titanic_full_df.groupby("Pclass").max()

titanic_full_df.groupby("Pclass").mean()["Age"]

titanic_full_df.groupby("Pclass").mean().loc["Работяги"]

titanic_full_df.groupby("Pclass").describe()["Age"]

titanic_full_df.groupby("Pclass").describe()["Age"].transpose()

titanic_full_df.groupby("Pclass")["Age"].agg(["min", "max", "std"])

titanic_full_df.groupby("Pclass").agg({"Age": np.mean, "PassengerId": "count"})

titanic_full_df.groupby(["Pclass", "Sex"]).mean()["Fare"]

ser1

for (index, value) in ser1.iteritems():
    print("Страна {}, место {}.".format(index, value))

for index, row in titanic_df.iterrows():
    print(index, row["Name"])

for group_name, group in titanic_full_df.groupby("Pclass"):
    print(group_name, group["Age"].mean())

df1 = pd.DataFrame(
    {
        'A': ['A0', 'A1', 'A2', 'A3'],
        'B': ['B0', 'B1', 'B2', 'B3'],
        'C': ['C0', 'C1', 'C2', 'C3'],
        'D': ['D0', 'D1', 'D2', 'D3']
    },
    index=[0, 1, 2, 3])

df2 = pd.DataFrame(
    {
        'A': ['A4', 'A5', 'A6', 'A7'],
        'B': ['B4', 'B5', 'B6', 'B7'],
        'C': ['C4', 'C5', 'C6', 'C7'],
        'D': ['D4', 'D5', 'D6', 'D7']
    },
    index=[4, 5, 6, 7])

df3 = pd.DataFrame(
    {
        'A': ['A8', 'A9', 'A10', 'A11'],
        'B': ['B8', 'B9', 'B10', 'B11'],
        'C': ['C8', 'C9', 'C10', 'C11'],
        'D': ['D8', 'D9', 'D10', 'D11']
    },
    index=[8, 9, 10, 11])

pd.concat([df1,df2,df3])

pd.concat([df1,df2,df3],axis=1)

left = pd.DataFrame({
    'key': ['K0', 'K1', 'K2', 'K3'],
    'A': ['A0', 'A1', 'A2', 'A3'],
    'B': ['B0', 'B1', 'B2', 'B3']
})

right = pd.DataFrame({
    'key': ['K0', 'K1', 'K2', 'K3'],
    'C': ['C0', 'C1', 'C2', 'C3'],
    'D': ['D0', 'D1', 'D2', 'D3']
})

pd.merge(left, right, how='inner', on='key')

import matplotlib.pyplot as plt
import seaborn as sns
from pylab import rcParams

%matplotlib inline
sns.set_style("ticks")
rcParams['figure.figsize'] = 12, 6

ser2

ser2.plot();

titanic_full_df.hist();

titanic_full_df["Age"].plot("kde", xlim=(titanic_full_df["Age"].min(), titanic_full_df["Age"].max()));

ser2.plot(kind="bar", fontsize=20);

titanic_full_df["Sex"].value_counts().plot(kind="pie", figsize=(7, 7), fontsize=20);

titanic_full_df["Pclass"].value_counts().plot(kind="pie", figsize=(7, 7), fontsize=20);

titanic_full_df[["Sex", "Survived"]].pivot_table(index=["Sex"], columns=["Survived"], aggfunc=len).plot(kind="bar");

titanic_full_df[["Age", "Survived"]].pivot_table(index=["Age"], columns=["Survived"], aggfunc=len).plot();