import pandas as pd import seaborn as sns from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA, KernelPCA from sklearn.cluster import MeanShift, KMeans

df = pd.read_csv("/content/sample_data/highest_earning_teams.csv")

df

df.dtypes

df.describe()

df.info()

df_t = df.sort_values(by="TotalUSDPrize", ascending=False)

sns.set(rc={"figure.figsize": (15,9)})

sns.barplot(data=df_t.head(10), x="TeamName", y="TotalUSDPrize")

def game_code(x): if x == "Counter-Strike: Global Offensive": return "CSGO" if x == "League of Legends": return "LOL" if x == "Heroes of the Storm": return "HOS" return x

df["Game"] = df["Game"].apply(lambda x: game_code(x)) df_g = pd.pivot_table(data=df, index=["Game"]).reset_index()

sns.boxplot(data=df_t, x="Game", y="TotalUSDPrize")

sns.barplot(data=df_g.sort_values(by="TotalUSDPrize", ascending=False), x="Game", y="TotalUSDPrize")

df_g

sns.scatterplot(data=df_t, x="TotalTournaments", y="TotalUSDPrize")

sns.heatmap(df_t.corr(), annot=True)

df_t["PricePerTournaments"] = df_t["TotalUSDPrize"] df_t["PricePerTournaments"] = df_t["PricePerTournaments"].apply(lambda x: round(x / df["TotalTournaments"], 2))

df_t = df_t.sort_values(by="PricePerTournaments", ascending=False)

sns.pairplot(df_t)

df_t

df

X = df.drop(columns=["TeamName", "TeamId"]) X = pd.get_dummies(X)

X

X = StandardScaler().fit_transform(X)

pca = PCA(n_components=2) pca = pca.fit(X)

X_p = pca.transform(X)

X_p

meanshift = MeanShift(max_iter=1000) meanshift = meanshift.fit(X_p)

X_p = pd.DataFrame(X_p)

X_p

sns.scatterplot(x=X_p[0], y=X_p[1], hue=meanshift.predict(X_p))

df["group"] = meanshift.predict(X_p)

sns.scatterplot(x=df["TotalTournaments"], y=df["TotalUSDPrize"], hue=df["group"])

df

max(meanshift.predict(X_p))

kpca = KernelPCA(n_components = 2, kernel="poly") kpca = kpca.fit(X)

X_kp = kpca.transform(X)

meanshift = MeanShift(max_iter=1000) meanshift = meanshift.fit(X_kp)

max(meanshift.predict(X_kp))

X_kp = pd.DataFrame(X_kp)

sns.scatterplot(x=X_kp[0], y=X_kp[1], hue=meanshift.predict(X_kp))

sns.scatterplot(x=df["TotalTournaments"], y=df["TotalUSDPrize"], hue=meanshift.predict(X_kp))

df["group"] = meanshift.predict(X_kp)

df

max(meanshift.predict(X_kp))

X

meanshift = MeanShift(max_iter=1000) meanshift = meanshift.fit(X)

X_w = meanshift.predict(X)

sns.scatterplot(x=df["TotalTournaments"], y=df["TotalUSDPrize"], hue=meanshift.predict(X))

max(meanshift.predict(X))

wcss = [] for i in range(1, 11): kmeans = KMeans(n_clusters=i, max_iter=1000) kmeans = kmeans.fit(X) wcss.append(kmeans.inertia_) sns.lineplot(x=range(1, 11), y=wcss)

wcss

pca = PCA(n_components=2) pca = pca.fit(X)

sns.lineplot(x = range(pca.n_components_), y = pca.explained_variance_ratio_)

X_p = pca.transform(X)

X_p

kmeans = KMeans(n_clusters=5) kmeans = kmeans.fit(X_p)

df["group"] = kmeans.predict(X_p)

sns.scatterplot(x=df_t["TotalTournaments"], y=df_t["TotalUSDPrize"], hue=kmeans.predict(X_p))

X_p = pd.DataFrame(X_p)

sns.scatterplot(x = X_p[0], y = X_p[1], hue=kmeans.predict(X_p))