In [1]:
import pandas as pd
import numpy as np
In [2]:
data = pd.read_csv("/data/mobile-sales-data.csv")
data.head()
Out[2]:
In [3]:
type(data)
Out[3]:
In [4]:
data.info()
In [5]:
data.sample(5)
Out[5]:
In [6]:
data.shape
Out[6]:
In [7]:
data["Salary"]
Out[7]:
In [8]:
data.iloc[:, 2]
Out[8]:
In [9]:
c = data["Salary"]
In [10]:
c.min(), c.max(), c.median()
Out[10]:
In [11]:
data[5:8]
Out[11]:
In [12]:
data.iloc[5:8, [0, 3]]
Out[12]:
In [13]:
data.columns
Out[13]:
In [14]:
data.iloc[:, [0, 3]]
Out[14]:
In [15]:
data[["Country", "Purchased"]]
Out[15]:
In [16]:
data["Country"].apply(lambda s:s.upper())
Out[16]:
In [17]:
data["COUNTRY"] = data["Country"].apply(lambda s:s.upper())
data
Out[17]:
In [18]:
data["SalAge"] = data.apply(lambda row: row["Salary"] / row["Age"], axis = 1)
data
Out[18]:
In [19]:
del(data["COUNTRY"])
del(data["SalAge"])
data
Out[19]:
In [20]:
data.dropna()
Out[20]:
In [21]:
data
Out[21]:
In [22]:
data.dropna(axis=1)
Out[22]:
In [23]:
data.fillna(data.mean())
Out[23]:
In [24]:
data["Age"].mean(), data["Salary"].mean()
Out[24]:
In [25]:
data.mean()
Out[25]:
In [26]:
data.fillna({"Age": 38.0,"Salary": 63777})
Out[26]:
In [27]:
data.index
Out[27]:
In [28]:
data["Age"].values
Out[28]:
In [29]:
data["Purchased"].value_counts()
Out[29]:
In [30]:
data.median()
Out[30]:
In [31]:
data.groupby("Country").median()
Out[31]:
In [32]:
data.groupby("Country")["Age"].median()
Out[32]:
In [33]:
data.groupby("Country")["Age"].agg([np.mean, np.median])
Out[33]:
In [34]:
data.groupby("Country").agg({"Age": np.mean, "Salary": np.median})
Out[34]:
In [35]:
data.groupby(["Country", "Purchased"]).mean()
Out[35]:
In [36]:
data
Out[36]:
In [37]:
data = data.fillna(data.median())
In [38]:
data
Out[38]:
In [39]:
data2 = pd.get_dummies(data, columns=["Country"])
In [40]:
del(data2["Purchased"])
In [41]:
pd.DataFrame(data2.values)
Out[41]:
In [42]:
from sklearn.preprocessing import StandardScaler
In [43]:
ss = StandardScaler()
data2_std = ss.fit_transform(data2.values)
In [44]:
pd.DataFrame(data2_std, columns = data2.columns)
Out[44]:
In [45]:
data.sort_values("Salary", ascending=False)
Out[45]:
In [46]:
data = pd.read_csv("/data/mobile-sales-data.csv")
data
Out[46]:
In [47]:
data[data["Country"] == "Spain"]
Out[47]:
In [48]:
data.query("Country == 'Spain'")
Out[48]:
In [49]:
movies = pd.read_csv("/data/ml-latest-small/movies.csv")
movies.head()
Out[49]:
In [50]:
ratings = pd.read_csv("/data/ml-latest-small/ratings.csv")
ratings.head()
Out[50]:
In [51]:
joined = pd.merge(movies, ratings, on="movieId")
joined.head()
Out[51]:
In [52]:
(joined
.groupby(["movieId", "title"])
.rating
.agg([len, np.mean])
.query("len >= 100")
.sort_values("mean", ascending = False)
.head(10)
.reset_index()[["movieId", "title", "mean"]]
)
Out[52]:
In [53]:
df = pd.read_csv("https://api.blockchain.info/charts/market-price?format=csv")
df.columns=["date", "price"]
df["datetime"] = pd.to_datetime(df["date"])
del df["date"]
df = df.set_index("datetime")
df.head()
Out[53]:
In [54]:
%matplotlib inline
df.plot()
Out[54]:
In [ ]: