【数据分析学习】Pandas学习记录

import pandas as pd
path = r'F:\数据分析专用\数据分析与机器学习\food_info.csv'
with open(path, 'r') as f:
    data = pd.read_csv(f)
    print(type(data))
    print(data.dtypes)
    print(help(pd.read_csv))

文件操作

print(data.head(3))
print(data.tail(3))
print(data.columns)

查看数据

data.sort_values('Carbohydrt_(g)', inplace=True)
print(data['Carbohydrt_(g)'])
# print(data)
data.sort_values('Carbohydrt_(g)', inplace=True, ascending=False)
print(data['Carbohydrt_(g)'])

数据排序

age = t_s['Age']
age_is_null = pd.isnull(age)
age_null_true = age[age_is_null]
age_null_count = len(age_null_true)
print(age_null_count)
#----------------------------------------
count_list = []
for i in age:
    if i != i:
        count_list.append(i)
print(len(count_list))

数据的筛选

mean_age = sum(t_s['Age'])/len(t_s['Age'])
print(mean_age)
#--------------------------------------------------
good_ages = t_s['Age'][age_is_null==False]
correct_mean_age = sum(good_ages)/len(good_ages)
print(correct_mean_age)
#---------------------------------------------
correct_mean_age = t_s['Age'].mean()
print(correct_mean_age)

数据的处理方法(平均数)

passenger_classes = {1, 2, 3}
faces_by_class = {}
for this_class in passenger_classes:
    pclass_rows = t_s[t_s['Pclass']==this_class]
    pclass_fares = pclass_rows['Fare']
    fare_for_class = pclass_fares.mean()
    faces_by_class[this_class] = fare_for_class
print(faces_by_class)
#--------------------------------------------------------
passenger_s = t_s.pivot_table(index='Pclass', values='Survived', aggfunc=np.mean)
print(passenger_s)
#--------------------------------------------------------
passenger_age = t_s.pivot_table(index='Pclass', values='Age')
print(passenger_age)
#--------------------------------------------------------
passenger_price = t_s.pivot_table(index='Pclass', values='Fare')
print(passenger_price)
#--------------------------------------------------------
port_stats = t_s.pivot_table(index='Embarked', values=['Fare', 'Survived'], aggfunc=np.sum)
print(port_stats)

数据透视表

---

def hundredth_row(column):
    hundredth_item = column.loc[99]
    return hundredth_item
 
hundredth_row = t_r.apply(hundredth_row)
print(hundredth_row)

自定义函数

def which_class(row):
    pclass = row['Pclass']
    if pd.isnull(pclass):
        return 'Unknown'
    elif pclass == 1:
        return "First Class"
    elif pclass == 2:
        return "Second Class"
    elif pclass == 3:
        return "Third Class"
 
classes = t_r.apply(which_class, axis=1)
print(classes)

自定义函数

---

import pandas as pd
path = r'F:\数据分析专用\数据分析与机器学习\fandango_score_comparison.csv'
with open(path, 'r', encoding='utf-8') as f:
    data = pd.read_csv(f)
    # print(data.dtypes)
    series_film = data['FILM']
    print(type(series_film))
    series_rt = data['RottenTomatoes']
    print(series_rt[0:5])
#--------------------------------------------------------------
from pandas import Series
film_names = series_film.values
print(type(film_names))
rt_scores = series_rt.values
series_custom = Series(rt_scores, index=film_names)
series_custom[['Minions (2015)', 'Leviathan (2014)']]

Series结构