pandas笔记--(1)--[DataFrames]

reference course at datacamp

1. 读取csv文件到dataframe中
2. 对dataframe的复制
3. 对dataframe中的数据赋予新的列名/更改列名
4. 对dataframe添加新的列名和列数据

import pandas as pd

gold = pd.read_csv("No_1.csv")
sliver = pd.read_csv("No_2.csv")
bronze = pd.read_csv("No_3.csv")

# Make a copy of gold: medals
medals = gold.copy()

# Create list of new column labels: new_labels
new_labels = ['NOC', 'Country', 'Gold']

# Rename the columns of medals using new_labels
medals.columns = new_labels

# Add columns 'Silver' & 'Bronze' to medals
medals['Silver'] = silver['Total']
medals['Bronze'] = bronze['Total']

• 使用glob函数获取类似文件名列表

from glob import glob

dataframes = []
filenames = glob("No_*.csv")
for filename in filenames:
    dataframes.append(pd.read_csv(filename))

# Import pandas
import pandas as pd

# Read 'monthly_max_temp.csv' into a DataFrame: weather1
weather1 =pd.read_csv("monthly_max_temp.csv", index_col="Month")

# Print the head of weather1
print(weather1.head())

# Sort the index of weather1 in alphabetical order: weather2
weather2 = weather1.sort_index()

# Print the head of weather2
print(weather2.head())

# Sort the index of weather1 in reverse alphabetical order: weather3
weather3 = weather1.sort_index(ascending=False)

# Print the head of weather3
print(weather3.head())

# Sort the index of weather1 numerically using the values of 'Max TemperatureF': weather4
weather4 = weather1.sort_values('Max TemperatureF')

# Print the head of weather4
print(weather4.head())

• reindex()

# Import pandas
import pandas as pd

# Reindex weather1 using the list year: weather2
weather2 = weather1.reindex(year)

# Print weather2
print(weather2)

# Reindex weather1 using the list year with forward-fill: weather3
# .ffill() method to replace the null values with the last preceding non-null value.
weather3 = weather1.reindex(year).ffill()

# Print weather3
print(weather3)