import pandas as pd
import matplotlib.pyplot as plt
import math
# DataFrame
print("====================创建dataFrame开始=======================")
df1 = pd.DataFrame([[1, 2, 3], [4, 5, 6]], index=['A', "B"], columns=["C", "D", "E"])
print(df1)
print(df1.values)
print(df1.T)
print(df1.shape)
print(df1.size)
# 前几行和后几行
print(df1.head(1))
print(df1.tail(1))
# 对一列数据进行分析，数量，平均值，方差，最小值，最大值
print(df1.describe())
# 选取某一行
print(df1.loc["A"])
print("====================创建dataFrame结束=======================")
print("====================read csv开始=======================")
data = pd.read_csv("resource/fff.csv", index_col="id")
print(data.head(3))
# print(broken_data[:3])
print(data.shape)
# 取出某列
print(data['x'][:3])
# 取出某些列
print(data[["x", "y"]][:3])
# 统计每个值出现的次数,可以添加过滤条件进行去重处理
print(data["x"].value_counts())
print("====================图形化开始=======================")
# 画出形状
data['x'].plot()
# data.plot()
# plt.show()
print(data.dtypes)
print("====================图形化结束=======================")
print("====================read csv结束=======================")
print("====================时间处理开始=======================")
timedata = pd.read_csv("resource/timestamp.csv")
print(timedata.dtypes)
# 转换成时间,过滤时间
local_time = pd.to_datetime(timedata["atime"], unit="s")
print(local_time)
condition = local_time > '2101-10-10'
print(timedata[condition])
print("====================时间处理结束=======================")
print("====================cal开始=======================")
x,y=4.47,6.55
x1,y1=4.1,7.61
rate = math.sqrt((x1-x)**2+(y1-y)**2)
print(rate)
print("====================cal结束=======================")
/Users/jun/anaconda3/envs/python36/bin/python /Applications/PyCharm.app/Contents/helpers/pydev/pydev_run_in_console.py 51520 51521 /Users/jun/PycharmProjects/liaokepython/wanmenpython/ipandas.py
Running /Users/jun/PycharmProjects/liaokepython/wanmenpython/ipandas.py
import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['/Users/jun/PycharmProjects/liaokepython', '/Users/jun/PycharmProjects/liaokepython/wanmenpython'])
====================创建dataFrame开始=======================
C D E
A 1 2 3
B 4 5 6
[[1 2 3]
[4 5 6]]
A B
C 1 4
D 2 5
E 3 6
(2, 3)
6
C D E
A 1 2 3
C D E
B 4 5 6
C D E
count 2.00000 2.00000 2.00000
mean 2.50000 3.50000 4.50000
std 2.12132 2.12132 2.12132
min 1.00000 2.00000 3.00000
25% 1.75000 2.75000 3.75000
50% 2.50000 3.50000 4.50000
75% 3.25000 4.25000 5.25000
max 4.00000 5.00000 6.00000
C 1
D 2
E 3
Name: A, dtype: int64
====================创建dataFrame结束=======================
====================read csv开始=======================
areaCode x y z time package tagId
id
1 1 4.65 6.55 1.2 2019/3/19 13:42 2209 B832
2 1 4.47 6.56 1.2 2019/3/19 13:42 2210 B832
3 1 4.47 6.55 1.2 2019/3/19 13:42 2211 B832
(169, 7)
id
1 4.65
2 4.47
3 4.47
Name: x, dtype: float64
x y
id
1 4.65 6.55
2 4.47 6.56
3 4.47 6.55
6.03 3
5.55 3
1.63 3
2.85 2
6.40 2
5.83 2
5.57 2
5.46 2
5.65 2
8.78 2
2.91 2
5.08 2
7.64 2
3.42 2
4.65 2
4.47 2
9.35 2
9.24 2
8.44 2
5.21 2
5.58 2
5.61 2
9.08 2
3.56 2
5.60 2
8.52 1
3.92 1
4.40 1
0.17 1
8.74 1
..
7.90 1
9.28 1
9.27 1
6.11 1
4.06 1
6.66 1
8.06 1
9.66 1
0.55 1
2.59 1
8.29 1
8.79 1
10.07 1
3.39 1
6.21 1
7.44 1
7.40 1
4.22 1
5.91 1
1.17 1
4.67 1
8.69 1
9.09 1
4.05 1
6.88 1
5.59 1
5.80 1
7.33 1
5.70 1
8.75 1
Name: x, Length: 141, dtype: int64
====================图形化开始=======================
areaCode int64
x float64
y float64
z float64
time object
package int64
tagId object
dtype: object
====================图形化结束=======================
====================read csv结束=======================
====================时间处理开始=======================
atime int64
btime int64
dtype: object
0 2110-06-13 20:25:51
1 2110-09-02 20:52:31
2 2100-12-10 15:05:51
Name: atime, dtype: datetime64[ns]
atime btime
0 4432134351 54335
1 4439134351 3454543
====================时间处理结束=======================
====================cal开始=======================
1.1227199116431494
====================cal结束=======================
PyDev console: starting.
Python 3.6.8 |Anaconda, Inc.| (default, Dec 29 2018, 19:04:46)
[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)] on darwin
