Dima martynov at 20

1.py

@@ -0,0 +1,6 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+df = pd.read_csv('works.csv')
+rows_count = df.shape[0]
+print("Всего записей:", rows_count)

2.py

@@ -0,0 +1,10 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+df = pd.read_csv('works.csv')
+def get_rows_with_gender(df: pd.DataFrame, gender: str) -> pd.DataFrame:
+    return df[df["gender"] == gender]
+females = get_rows_with_gender(df, "Женский")
+males = get_rows_with_gender(df, "Мужской")
+print("Всего женщин:", females.shape[0])
+print("Всего мужчин:", males.shape[0])

3.py

@@ -0,0 +1,11 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+df = pd.read_csv('works.csv')
+def get_rows_with_gender(df: pd.DataFrame, gender: str) -> pd.DataFrame:
+    return df[df["gender"] == gender]
+females = get_rows_with_gender(df, "Женский")
+males = get_rows_with_gender(df, "Мужской")
+no_none_skills_count = df["skills"].count()
+
+print("Значений в столбце skills не NAN:", no_none_skills_count)

4.py

@@ -0,0 +1,10 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+df = pd.read_csv('works.csv')
+def get_rows_with_gender(df: pd.DataFrame, gender: str) -> pd.DataFrame:
+    return df[df["gender"] == gender]
+females = get_rows_with_gender(df, "Женский")
+males = get_rows_with_gender(df, "Мужской")
+skills = df[df["skills"].notna()]
+print("Все заполненные скиллы:\n", skills["skills"])

5.py

@@ -0,0 +1,11 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+
+works = pd.read_csv("works.csv")
+head = works.head(5)
+tail = works.tail(5)
+
+skills_bool = works["skills"].str.lower().str.contains("python|питон") & works["skills"].notnull()
+print(works[skills_bool]["salary"])

6.py

@@ -0,0 +1,11 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+df = pd.read_csv('works.csv')
+def get_rows_with_gender(df: pd.DataFrame, gender: str) -> pd.DataFrame:
+    return df[df["gender"] == gender]
+females = get_rows_with_gender(df, "Женский")
+males = get_rows_with_gender(df, "Мужской")
+pr = [i / 10 for i in range(1, 11)]
+print("Женщины:\n", females["salary"].quantile(pr))
+print("Мужчины\n", males["salary"].quantile(pr))

7.py

@@ -0,0 +1,20 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as mp
+
+works = pd.read_csv("works.csv")
+men_salary = works.query("gender == 'Мужской'").groupby("educationType").agg("mean").reset_index()
+women_salary = works.query("gender == 'Женский'").groupby("educationType").agg("mean").reset_index()
+
+educationTypes = men_salary["educationType"].values
+men_salaries = men_salary["salary"].values
+women_salary = women_salary["salary"].values
+
+index = np.arange(len(educationTypes))
+
+bw = 0.4
+mp.bar(index-bw/2, men_salaries, bw, color="b", label="Средняя зарплата мужчин")
+mp.bar(index+bw/2, women_salary, bw, color="r", label="Средняя зарплата женщин")
+mp.xticks(index, educationTypes, rotation=45)
+mp.legend()
+mp.show()

8.py

@@ -0,0 +1,30 @@
+import pandas as pd
+
+
+def get_match_count(first_list, second_list):
+    return len(list((filter(lambda x: contains(x[0], x[1]) or contains(x[1], x[0]), zip(first_list, second_list)))))
+
+
+def contains(sub_text, text):
+    words = sub_text.replace('-', ' ').split(' ')
+    for word in words:
+        if word in text:
+            return True
+    return False
+
+
+def get_top(source, search_field, return_field, value):
+    return source[source[search_field].str.contains(value)][return_field].value_counts().head(5)
+
+
+data = pd.read_csv('works.csv').dropna().apply(lambda x: x.astype(str).str.lower())
+count = len(data)
+mismatch_count = count - get_match_count(data["jobTitle"], data["qualification"])
+
+print(f"Всего людей: {count}.")
+print(f"Людей с несовпадающими профессией и должностью: {mismatch_count}.")
+print(f"Что составляет {mismatch_count / count:.0%} от общего числа.")
+print("\nТоп 5 квалификаций менеджеров:")
+print(get_top(data, "jobTitle", "qualification", "менеджер"))
+print("\nТоп 5 должностей инженеров:")
+print(get_top(data, "qualification", "jobTitle", "инженер"))