pandas dataframe from csv code example

Example 1: command to read file in python using pandas

import panda as pd 

file_csv = pd.read_csv("file path")  ## as csv format
file_excel = pd.read_excel("file path") ## as excel format
file_json = pd.read_json("file path") ## as json format
file_html = pd.read_html("file path") ## as html format
file_localClipboard = pd.read_clipboard("file path") ## as clipboard format
file_MSExcel = pd.read_excel("file path") ## as excel format
file_HDF5 = pd.read_hdf("file path") ## as hdf5 fomrmat
file_Feather = pd.read_feather("file path") ## as feather format
file_msgpack = pd.read_msgpack("file path") ## as msgpack format
file_stata = pd.read_stata("file path") ## as stata format
file_SAS = pd.read_sas("file path") ## as SAS format
file_paythonPickle = pd.read_pickle("file path") ## as paython_pickle format
file_SQL = pd.read_sql("file path") ## as sql format
file_google_big_query = pd.read_gbq("file path") ## as google big query

Example 2: save dataframe to csv

df.to_csv(file_name, sep='\t')

Example 3: how to set up dataframe from csv

import pandas as pd

column_names = ['sepel lengh', 'sepel width', 'petal lengh', 'petal width', 'class']
iris = pd.read_csv('iris.csv', names=column_names)

print(iris)

Example 4: pandas read csv

import pandas as pd
cereal_df = pd.read_csv("/tmp/tmp07wuam09/data/cereal.csv")
cereal_df2 = pd.read_csv("data/cereal.csv")

# Are they the same?
print(pd.DataFrame.equals(cereal_df, cereal_df2))

Example 5: convert csv to pandas dataframe

import pandas as pd
df = pd.read_csv("sample_data.csv")

# .csv file format
column1,column2
1,2
3,4
5,6

# pandas dataframe
   column1  column2
0        1        2
1        3        4
2        5        6

Example 6: pandas go through csv file

data = pd.read_csv(
    "data/files/complex_data_example.tsv",      # relative python path to subdirectory
    sep='\t'           # Tab-separated value file.
    quotechar="'",        # single quote allowed as quote character
    dtype={"salary": int},             # Parse the salary column as an integer 
    usecols=['name', 'birth_date', 'salary'].   # Only load the three columns specified.
    parse_dates=['birth_date'],     # Intepret the birth_date column as a date
    skiprows=10,         # Skip the first 10 rows of the file
    na_values=['.', '??']       # Take any '.' or '??' values as NA
)