30 things you can do with Pandas

import pandas as pd df=pd.read_csv('test.csv') # read a test file to dataframe

pd.DataFrame.from_csv(“csv_file”) or pd.read_csv(“csv_file”)

pd.read_excel("excel_file")

df.to_csv("data.csv", sep=",", index=False)

pd.DataFrame(data,columns=[])

df.dtypes

df.info()

print(df.describe())

df.columns

df.dropna(axis=0, how='any')

df.replace(to_replace=None, value=None)

pd.isnull(object)

df.drop('feature_variable_name', axis=1)

pd.to_numeric(df["feature_name"], errors='coerce')

df.as_matrix()

df.head(n)

df.tail(n)

df.loc[feature_name]

df["height"].apply(lambda height: 2 * height)

df.rename(columns = {df.columns[2]:'size'}, inplace=True)

df["job"].value_counts()

df["name"].unique()

new_df = df[["name", "size"]]

# Sum of values in a data frame df.sum() # Lowest value of a data frame df.min() # Highest value df.max() # Index of the lowest value df.idxmin() # Index of the highest value df.idxmax() # Statistical summary of the data frame, with quartiles, median, etc. df.describe() # Average values df.mean() # Median values df.median() # Correlation between columns df.corr() # To get these values for only one column, just select it like this# df["size"].median()

df.sort_values(ascending = False)

df[df["size"] == 5]

df.loc([0], ['size'])

pd.crosstab(df["y"],df["z"])

df["size"].plot()

df.shape

df.sample(n)