Python-Pandas(1)数据读取与显示,数据样本行列选取

1
2
3
4
import pandas
food_info = pandas.read_csv("food_info.csv")
#print(type(food_info))
print food_info.dtypes

1
2
3
4
5
#first_rows = food_info.head()
#print first_rows
#print(food_info.head(3))
#print food_info.columns
#print food_info.shape

1
2
3
4
5
6
7
8
#pandas uses zero-indexing
#Series object representing the row at index 0.
#print food_info.loc[0]
# Series object representing the seventh row.
#food_info.loc[6]
# Will throw an error: "KeyError: 'the label [8620] is not in the [index]'"
#food_info.loc[8620]
#The object dtype is equivalent to a string in Python

1
2
3
4
5
6
#object - For string values
#int - For integer values
#float - For float values
#datetime - For time values
#bool - For Boolean values
#print(food_info.dtypes)

1
2
3
4
5
6
7
8
# Returns a DataFrame containing the rows at indexes 3, 4, 5, and 6.
#food_info.loc[3:6]
# Returns a DataFrame containing the rows at indexes 2, 5, and 10. Either of the following approaches will work.
# Method 1
#two_five_ten = [2,5,10] 
#food_info.loc[two_five_ten]
# Method 2
#food_info.loc[[2,5,10]]

1
2
3
4
5
6
# Series object representing the "NDB_No" column.
#ndb_col = food_info["NDB_No"]
#print ndb_col
# Alternatively, you can access a column by passing in a string variable.
#col_name = "NDB_No"
#ndb_col = food_info[col_name]

1
2
3
4
5
6
#columns = ["Zinc_(mg)", "Copper_(mg)"]
#zinc_copper = food_info[columns]
#print zinc_copper
#print zinc_copper
# Skipping the assignment.
#zinc_copper = food_info[["Zinc_(mg)", "Copper_(mg)"]]

1
2
3
4
5
6
7
8
9
10
#print(food_info.columns)
#print(food_info.head(2))
col_names = food_info.columns.tolist()
#print col_names
gram_columns = []
for c in col_names:
if c.endswith("(g)"):
gram_columns.append(c)
gram_df = food_info[gram_columns]
print(gram_df.head(3))