import pandas as pd
import matplotlib.pyplot as plt
from src.utils.utils import utils
# header指定用哪一行作列名, index_col指定用作索引的列
# https://blog.csdn.net/weixin_38546295/article/details/83537558
df_pages = pd.read_excel(utils.getDataDir("/pandas/头马助手使用分析_页面分析.xlsx"),
header=2,
index_col=0)
print(df_pages.dtypes)
print(df_pages)
# 百分比转化为float类型用于排序
df_pages_quit = df_pages["退出率"].str.strip('%').astype(float) / 100
print(df_pages_quit.sort_values(ascending=False))
pb = NSPasteboard.generalPasteboard()
pb.clearContents()
# TODO 如果传入图片
a = NSArray.arrayWithObject_(text)
return pb.writeObjects_(a)
# 将bytes数据还原为图片
def image_from_bytes(raw):
from_img = Image.frombytes(img.mode, img.size, raw)
return from_img
if __name__ == '__main__':
text = "激战"
setClip(text)
# bytes字节符，打印以b开头。
# encode() will result in a sequence of bytes. decode() decodes a stream of bytes to a string object
# bytes([source[, encoding[, errors]]]): source to initialize the array of bytes. if source is a string, the encoding of the string.
print(bytes(get_paste_img_file()).decode("utf-8"))
data = get_paste_img_file()
writeToFile(data)
# 将bytes数据还原为图片
# TODO 如何将剪切板获取的数据转成合适的bytes
img = Image.open(utils.getDataDir("/images/gushi.jpeg"))
raw = img.tobytes()
img_out = image_from_bytes(raw)
img_out.show()
import pandas as pd
from src.utils.utils import utils
# https://pandas.pydata.org/docs/getting_started/intro_tutorials/03_subset_data.html#min-tut-03-subset
titanic = pd.read_csv(utils.getDataDir("/pandas/titanic.csv"))
# To select a single column, use square brackets
print(titanic["Age"])
print(titanic["Age"].max())
print(titanic["Age"].min())
# Have a look at the shape of titanic["Age"]
# shape is an attribute of a pandas Series so we don't need to add round brackets
print(titanic["Age"].shape)
# We can select two columns at the same time, use a list of column names within the selection brackets []
print(titanic[["Age", "Sex"]])
print(titanic[["Age", "Sex"]].shape)
# To select rows based on a conditional expression, use a condition inside the selection brackets [].
print(titanic[titanic["Age"] > 35])
# Another conditional expression
print(titanic[titanic["Pclass"].isin([2, 3])])
# When combining multiple conditional statements, each condition must be surrounded by parentheses ().
# Moreover, you can not use or/and but need to use the or operator | and the and operator &.
print(titanic[(titanic["Pclass"] == 2) | (titanic["Pclass"] == 3)])
# To select rows if Age is not NA
import pandas as pd
from src.utils.utils import utils
import matplotlib.pyplot as plt
pd.set_option('display.max_columns',200) #设置显示列数
pd.set_option('display.max_rows',10) #设置显示行数
df = pd.read_csv(utils.getDataDir("/pandas/content_search_query2020-04-08.csv"))
print(df)
# 按照预测行业进行统计
# 'DataFrame' object has no attribute 'value_counts', only 'Series' has.
print(df["预测行业"].value_counts())
# 筛选出买家数>0的数据
# print(df[df["买家数"] > 0])
# 筛选出曝光点击率 > 0.3的查询词
df["曝光点击率"] = df["曝光点击率"].str.strip('%').astype(float)/100
# print(df["曝光点击率"])
# print(df[df["曝光点击率"] > 0.3])
# 计算搜索词的平均uv
# print(df["搜索uv"].mean())
print(df[df["曝光点击率"] > 0.3])
df[df["曝光点击率"] > 0.3].plot()
plt.show()
df = df.rename(columns={"搜索uv": "search uv", "搜索pv": "search pv"})
import pandas as pd
import matplotlib.pyplot as plt
from src.utils.utils import utils
# https://pandas.pydata.org/docs/getting_started/intro_tutorials/04_plotting.html
# Column(s) to use as the row labels of the DataFrame, either given as string name or column index.
# Note: index_col=False can be used to force pandas to not use the first column as the index
# index_col=0 define the first (0th) column as index of the resulting DataFrame
# parse_dates convert the dates in the column to Timestamp objects, respectively
# air_quality = pd.read_csv(utils.getDataDir("/pandas/air_quality_no2.csv"), parse_dates=True)
air_quality = pd.read_csv(utils.getDataDir("/pandas/air_quality_no2.csv"),
index_col=0,
parse_dates=True)
# print(air_quality)
print(air_quality)
print(air_quality.dtypes)
# a quick visual check of the data.
air_quality.plot()
plt.show()
# plot only the columns of the data table with the data from Paris.
air_quality["station_paris"].plot()
plt.show()
# Visually compare the 𝑁02 values measured in London versus Paris.
# Scatter create a scatter plot（散点图）with varying marker point size and color.
air_quality.plot.scatter(x="station_london", y="station_paris", alpha=0.5)
import pandas as pd
import matplotlib.pyplot as plt
from src.utils.utils import utils
df_income = pd.read_csv(
utils.getDataDir("/pandas/头马助手收入明细2020-03-25至2020-04-24.csv"))
print(df_income)
# key中可能包含空格，可以通过keys()方法输出查看
print("近31天总收入")
print(format(df_income["总收入(元)"].sum(), ".2f"))
print("近31天平均每天收入")
all = format(df_income["总收入(元)"].mean(), ".2f")
print(all)
print("近31天原生视频总收入")
# format产出的是str
原生视频 = format(df_income["原生视频"].sum(), ".2f")
print(原生视频)
print("近31天格子广告总收入")
格子广告 = format(df_income["格子广告"].sum(), ".2f")
print()
print("近31天banner总收入")
banner = format(df_income["banner"].sum(), ".2f")
print(banner)
# series = pd.Series([原生视频,格子广告,banner], index=["原生视频", "格子广告", "banner"], name="总收入")
import pytesseract
# https://tesseract-ocr.github.io/tessdoc/Data-Files
# Error opening data file /usr/local/share/tessdata/chi_sim.traineddata
from src.utils.utils import utils
try:
import Image
except ImportError:
from PIL import Image
image_path = utils.getDataDir("/images/gushi.png")
# CASE 1
# image = Image.open(image_path)
# 对图片进行阈值过滤,然后保存
# image = image.point(lambda x: 0 if x<143 else 255)
# image.save('./new.png')
# lang 指定中文简体
# text = pytesseract.image_to_string(image, lang='chi_sim')
# print(text)
# CASE 2
# 通过text文件批量处理图片
# text = pytesseract.image_to_string('../../../../data/images/images.txt', lang='chi_sim')
# print(text)
# CASE 3
# 直接通过图片路径处理图片，跳过Image open
import pandas as pd
from src.utils.utils import utils
# Read data from CSV file
# pd_csv.csv
# 1,2,3
# 2,3,4
# 7,8,9
df = pd.read_csv(utils.getDataDir("/pandas/pd_csv.csv"))
print(df)
# 1 2 3
# 0 2 3 4
# 1 7 8 9
# Read a large amount of data from CSV file
df = pd.read_csv(utils.getDataDir("/pandas/pandas.csv"))
print(df)
print(df.head(3))
# A check on how pandas interpreted each of the column data types
# When asking for the dtypes, no brackets are used! dtypes is an attribute of a DataFrame and Series.
print(df.dtypes)
# Read data from Excel
# pip3.7 install xlrd if ImportError: Missing optional dependency 'xlrd'.
df = pd.read_excel(utils.getDataDir("/pandas/simple.xlsx"),
sheet_name="Sheet1")
print(df)
print(df.info())