熊猫备忘单

import pandas as pd

# create a pandas series from a lists = pd.series([1, 2, 3, 4])

0    11    22    33    4dtype: int64

# create a dataframe from a dictionarydata = {'name': ['alice', 'bob', 'charlie'], 'age': [24, 27, 22], 'city': ['new york', 'london', 'berlin']}df = pd.dataframe(data)

      name  age      city0    alice   24  new york1      bob   27    london2  charlie   22    berlin

data = {'col1': [1, 2, 3], 'col2': [4, 5, 6]}df = pd.dataframe(data)

data = [[1, 2, 3], [4, 5, 6]]df = pd.dataframe(data, columns=["a", "b", "c"])

   a  b  c0  1  2  31  4  5  6

# inspecting the dataframeprint(df.head())print(df.tail())print(df.info())print(df.describe())

   a  b  c0  1  2  31  4  5  6   a  b  c0  1  2  31  4  5  6<class 'pandas.core.frame.dataframe'>rangeindex: 2 entries, 0 to 1data columns (total 3 columns): #   column  non-null count  dtype---  ------  --------------  ----- 0   a       2 non-null      int64 1   b       2 non-null      int64 2   c       2 non-null      int64dtypes: int64(3)memory usage: 128.0 bytes       a    b    ccount  2.0  2.0  2.0mean   2.5  3.5  4.5std    2.1  2.1  2.1min    1.0  2.0  3.025%    1.5  2.5  3.550%    2.0  3.0  4.075%    2.5  3.5  4.5max    4.0  5.0  6.0

# dot notationprint(df.a)# bracket notationprint(df["b"])

# using iloc (index-based)print(df.iloc[0])  # access first row# using loc (label-based)print(df.loc[0])  # access first row using label

# select specific rows and columnssubset = df.loc[0:1, ["a", "c"]]

   a  c0  1  31  4  6

df['d'] = [7, 8]  # adding a new column

df['a'] = df['a'] * 2  # modify the 'a' column

df = df.drop(columns=['d'])  # dropping a columndf = df.drop(index=1)  # dropping a row by index

df = df.fillna(0)  # fill missing data with 0df = df.dropna()  # drop rows with any missing values

# grouping by a column and calculating the sumgrouped = df.groupby('city').sum()

# aggregating data using meandf.groupby('city').mean()

# sorting by a column in ascending orderdf_sorted = df.sort_values(by='age')# sorting by multiple columnsdf_sorted = df.sort_values(by=['age', 'name'], ascending=[true, false])

df['rank'] = df['age'].rank()

df1 = pd.dataframe({'a': ['a0', 'a1', 'a2'], 'b': ['b0', 'b1', 'b2']})df2 = pd.dataframe({'a': ['a0', 'a1', 'a2'], 'c': ['c0', 'c1', 'c2']})merged_df = pd.merge(df1, df2, on='a')

df1 = pd.DataFrame([[1, 2], [3, 4]], columns=['A', 'B'])df2 = pd.DataFrame([[5, 6], [7, 8]], columns=['A', 'B'])concat_df = pd.concat([df1, df2], axis=0)