def to_space(filename, filename_txt):
df = count_lines.read_file(filename)
city = list(df["city"])
town = list(df["town"])
newtext = open(filename_txt, "w", encoding="utf-8")
# 文字と文字の間をspaceにして新しいテキストに記載
for i in range(len(df)):
newtext.write(str(city[i]) + " " + str(town[i]) + "\n")
newtext.close()
return newtext
def extract_fromm_ton(file, newfilename, mlines, nlines):
df = count_lines.read_file(filename)
city = list(df["city"])
town = list(df["town"])
newtext = open(newfilename, "w", encoding="utf-8")
for i in range(mlines, nlines):
newtext.write(str(city[i])+" "+str(i)+"\n")
print(str(city[i])+" "+str(town[i])+"\n")
newtext.close()
return newtext
def extract_first_column(filename, newfilename):
df = count_lines.read_file(filename)
city = list(df["city"])
city_list = list(set(city)) # 重複を除く
newtext = open(newfilename, "w", encoding="utf-8")
for i in range(len(city_list)):
newtext.write(str(city_list[i]) + "\n")
print(str(city_list[i]) + "\n")
newtext.close()
return newtext
def extract_lines(filename, fromnline, newfilename):
df = count_lines.read_file(filename)
city = list(df["city"])
town = list(df["town"])
newtext = open(newfilename, "w", encoding="utf-8")
# n番目までのデータを表示して新しいテキストに書き込む
for i in range(fromnline):
newtext.write(str(city[i]) + " " + str(town[i]) + "\n")
print(str(city[i]) + " " + str(town[i]) + "\n")
newtext.close()
return newtext
def frequency(filename, newfilename):
df = count_lines.read_file(filename)
vc = df["town"].value_counts()
total = len(vc)
text = open(newfilename, "w", encoding="utf-8")
for i in range(total):
frequency = vc[i] / total
print(vc.index[i] + " :frequency is" + str(frequency))
text.write(vc.index[i] + ": frequency is " + str(frequency) + "\n")
text.close()
return text
def extract_lastnlines(filename, toline, newfilename):
df = count_lines.read_file(filename)
city = list(df["city"])
town = list(df["town"])
newtext = open(newfilename, "w", encoding="utf-8")
# countでは最後から数えるのでマイナスを指定し、rangeは0からの範囲なので-1して後ろから数えるように指定
for i in range(nlines):
count = -(i + 1)
newtext.write(str(city[count]) + " " + str(town[count]) + "\n")
print(str(city[count]) + " " + str(town[count]) + "\n")
newtext.close()
return newtext
def extract_first_list(filename, newfilename):
df = count_lines.read_file(filename)
cities = df["city"].unique()
with open(newfilename, mode="w") as f:
f.write('\n'.join(cities))
return cities
def extract_lines(filename, fromline, toline):
df = count_lines.read_file(filename)
print(df[fromline:toline])
extractlines = df[fromline:toline]
return extractlines
def count_cities(filename):
df = count_lines.read_file(filename)
cities = list(df["city"])
dict_cities = count_string(cities)
return dict_cities
def count_string(filename):
df = count_lines.read_file(filename)
vc = df["city"].value_counts()
return vc
def extract_lines(filename, fromnline):
df = count_lines.read_file(filename)
nrows = df.tail(fromnline)
return nrows